Search Results for author: Jian Yang

Found 272 papers, 111 papers with code

Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning

no code implementations ECCV 2020 Xi Cheng, Zhen-Yong Fu, Jian Yang

In the past few years, we have witnessed the great progress of image super-resolution (SR) thanks to the power of deep learning.

Image Super-Resolution

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection

1 code implementation11 Mar 2024 YuXuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang

To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.

 Ranked #1 on 2D Object Detection on SARDet-100K (using extra training data)

Object object-detection +1

Harmonious Group Choreography with Trajectory-Controllable Diffusion

no code implementations10 Mar 2024 Yuqin Dai, Wanlu Zhu, Ronghui Li, Zeping Ren, Xiangzheng Zhou, Xiu Li, Jun Li, Jian Yang

Specifically, to tackle dancer collisions, we introduce a Dance-Beat Navigator capable of generating trajectories for multiple dancers based on the music, complemented by a Distance-Consistency loss to maintain appropriate spacing among trajectories within a reasonable threshold.

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

1 code implementation5 Mar 2024 Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang

To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.

Knowledge Distillation Prompt Engineering +1

Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging

1 code implementation28 Feb 2024 Wei zhang, Hongcheng Guo, Anjie Le, Jian Yang, Jiaheng Liu, Zhoujun Li, Tieqiao Zheng, Shi Xu, Runqiang Zang, Liangfan Zheng, Bo Zhang

Log parsing, which entails transforming raw log messages into structured templates, constitutes a critical phase in the automation of log analytics.

Log Parsing

Scene Prior Filtering for Depth Map Super-Resolution

no code implementations21 Feb 2024 Zhengxue Wang, Zhiqiang Yan, Ming-Hsuan Yang, Jinshan Pan, Jian Yang, Ying Tai, Guangwei Gao

Specifically, we design an All-in-one Prior Propagation that computes the similarity between multi-modal scene priors, i. e., RGB, normal, semantic, and depth, to reduce the texture interference.

Depth Map Super-Resolution

A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence

no code implementations20 Feb 2024 Penghai Zhao, Xin Zhang, Ming-Ming Cheng, Jian Yang, Xiang Li

In response to these concerns, this Analysis aims to provide a thorough review of reviews in the PAMI field from diverse perspectives.

Language Modelling Large Language Model

C-ICL: Contrastive In-context Learning for Information Extraction

no code implementations17 Feb 2024 Ying Mo, Jian Yang, Jiahao Liu, Shun Zhang, Jingang Wang, Zhoujun Li

Recently, there has been increasing interest in exploring the capabilities of advanced large language models (LLMs) in the field of information extraction (IE), specifically focusing on tasks related to named entity recognition (NER) and relation extraction (RE).

In-Context Learning Miscellaneous +4

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models

1 code implementation8 Feb 2024 Senmao Li, Joost Van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang

However, these models struggle to effectively suppress the generation of undesired content, which is explicitly requested to be omitted from the generated image in the prompt.

VIPTR: A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition

1 code implementation18 Jan 2024 Xianfu Cheng, Weixiao Zhou, Xiang Li, Xiaoming Chen, Jian Yang, Tongliang Li, Zhoujun Li

In this work, we propose the VIsion Permutable extractor for fast and efficient scene Text Recognition (VIPTR), which achieves an impressive balance between high performance and rapid inference speeds in the domain of STR.

Scene Text Recognition

MLAD: A Unified Model for Multi-system Log Anomaly Detection

no code implementations15 Jan 2024 Runqiang Zang, Hongcheng Guo, Jian Yang, Jiaheng Liu, Zhoujun Li, Tieqiao Zheng, Xu Shi, Liangfan Zheng, Bo Zhang

In spite of the rapid advancements in unsupervised log anomaly detection techniques, the current mainstream models still necessitate specific training for individual system datasets, resulting in costly procedures and limited scalability due to dataset size, thereby leading to performance bottlenecks.

Anomaly Detection Relational Reasoning +1

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

no code implementations13 Jan 2024 Linzheng Chai, Jian Yang, Tao Sun, Hongcheng Guo, Jiaheng Liu, Bing Wang, Xiannian Liang, Jiaqi Bai, Tongliang Li, Qiyao Peng, Zhoujun Li

To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.

Few-Shot Learning Language Modelling +1

RotationDrag: Point-based Image Editing with Rotated Diffusion Features

1 code implementation12 Jan 2024 Minxing Luo, Wentao Cheng, Jian Yang

Our method tracks handle points more precisely by utilizing the feature map of the rotated images, thus ensuring precise optimization and high image fidelity.

Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch

1 code implementation ACM Transactions on Multimedia Computing, Communications, and Applications 2024 Mingyu Li, Tao Zhou, Zhuo Huang, Jian Yang, Jie Yang, Chen Gong

Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data.

Domain Adaptation

Exploring Multi-Modal Control in Music-Driven Dance Generation

no code implementations1 Jan 2024 Ronghui Li, Yuqin Dai, Yachao Zhang, Jun Li, Jian Yang, Jie Guo, Xiu Li

Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process.

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL

1 code implementation18 Dec 2023 Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.

SQL Parsing Text-To-SQL

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

1 code implementation17 Dec 2023 Xiaoqi An, Lin Zhao, Chen Gong, Nannan Wang, Di Wang, Jian Yang

In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?"

Pose Estimation

Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models

1 code implementation15 Dec 2023 Senmao Li, Taihang Hu, Fahad Shahbaz Khan, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, Jian Yang

This finding inspired us to omit the encoder at certain adjacent time-steps and reuse cyclically the encoder features in the previous time-steps for the decoder.

Knowledge Distillation

Divide and Conquer: Hybrid Pre-training for Person Search

1 code implementation13 Dec 2023 Yanling Tian, Di Chen, Yunan Liu, Jian Yang, Shanshan Zhang

To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data.

Human Detection Person Search

M2C: Towards Automatic Multimodal Manga Complement

1 code implementation26 Oct 2023 Hongcheng Guo, Boyang Wang, Jiaqi Bai, Jiaheng Liu, Jian Yang, Zhoujun Li

In other words, the Multimodal Manga Complement (M2C) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for vision and language understanding.

Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems

no code implementations16 Oct 2023 Yunli Wang, Zhiqiang Wang, Jian Yang, Shiyang Wen, Dongying Kong, Han Li, Kun Gai

Concretely, we employ multi-task learning to adaptively combine the optimization of relaxed and full targets, which refers to metrics Recall@m@k and OPA respectively.

Learning-To-Rank Multi-Task Learning +1

Continual Learning via Manifold Expansion Replay

no code implementations12 Oct 2023 Zihao Xu, Xuan Tang, Yufei Shi, Jianfeng Zhang, Jian Yang, Mingsong Chen, Xian Wei

To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER).

Continual Learning Management

Interpretable Traffic Event Analysis with Bayesian Networks

no code implementations10 Oct 2023 Tong Yuan, Jian Yang, Zeyi Wen

With a concrete case study, our framework can derive a Bayesian Network from a dataset based on the causal relationships between weather and traffic events across the United States.

Amazing Combinatorial Creation: Acceptable Swap-Sampling for Text-to-Image Generation

no code implementations3 Oct 2023 Jun Li, Zedong Zhang, Jian Yang

Our experiments focus on text pairs of objects from ImageNet, and our results demonstrate that our approach outperforms recent methods such as Stable-Diffusion2, DALLE2, ERNIE-ViLG2 and Bing in generating novel and surprising object images, even when the associated concepts appear to be implausible, such as lionfish-abacus.

Object Text-to-Image Generation

Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation

no code implementations15 Sep 2023 Xianjie Wu, Jian Yang, Tongliang Li, Di Liang, Shiwei Zhang, Yiyang Du, Zhoujun Li

To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (u-EIDG).

Dialogue Generation

TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer

1 code implementation12 Sep 2023 Haibo Chen, Lei Zhao, Jun Li, Jian Yang

To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects.

Style Transfer

SGNet: Salient Geometric Network for Point Cloud Registration

no code implementations12 Sep 2023 Qianliang Wu, Yaqing Ding, Lei Luo, Shuo Gu, Chuanwei Zhou, Jin Xie, Jian Yang

These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify key correspondences for successful registration.

Point Cloud Registration

Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning

no code implementations7 Sep 2023 Zehua Ren, Yongheng Sun, Miaomiao Wang, Yuying Feng, Xianjun Li, Chao Jin, Jian Yang, Chunfeng Lian, Fan Wang

In this paper, we propose to leverage the idea of counterfactual reasoning coupled with the auxiliary task of brain tissue segmentation to learn fine-grained positional and morphological representations of PWMLs for accurate localization and segmentation.

counterfactual Counterfactual Reasoning +2

Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering

no code implementations1 Sep 2023 Shiqi Yang, Yaxing Wang, Joost Van de Weijer, Luis Herranz, Shangling Jui, Jian Yang

We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity.

Clustering Source-Free Domain Adaptation

RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion

no code implementations1 Sep 2023 Zhiqiang Yan, Xiang Li, Le Hui, Zhenyu Zhang, Jun Li, Jian Yang

To tackle these challenges, we explore a repetitive design in our image guided network to gradually and sufficiently recover depth values.

Depth Completion Depth Estimation +1

mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning

no code implementations17 Aug 2023 Ying Mo, Jian Yang, Jiahao Liu, Qifan Wang, Ruoyu Chen, Jingang Wang, Zhoujun Li

A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations.

Contrastive Learning named-entity-recognition +2

Dual-Stream Diffusion Net for Text-to-Video Generation

no code implementations16 Aug 2023 Binhui Liu, Xin Liu, Anbo Dai, Zhiyong Zeng, Dan Wang, Zhen Cui, Jian Yang

In particular, the designed two diffusion streams, video content and motion branches, could not only run separately in their private spaces for producing personalized video variations as well as content, but also be well-aligned between the content and motion domains through leveraging our designed cross-transformer interaction module, which would benefit the smoothness of generated videos.

Text-to-Video Generation Video Generation

Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model

1 code implementation3 Aug 2023 Fu Lin, Xuexiong Luo, Jia Wu, Jian Yang, Shan Xue, Zitong Wang, Haonan Gong

Then, two competing student models trained by normal and abnormal graphs respectively fit graph representations of the teacher model in terms of node-level and graph-level representation perspectives.

Anomaly Detection

Creative Birds: Self-Supervised Single-View 3D Style Transfer

2 code implementations ICCV 2023 Renke Wang, Guimin Que, Shuo Chen, Xiang Li, Jun Li, Jian Yang

Our focus lies primarily on birds, a popular subject in 3D reconstruction, for which no existing single-view 3D transfer methods have been developed. The method we propose seeks to generate a 3D mesh shape and texture of a bird from two single-view images.

3D Reconstruction Style Transfer

FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Models

1 code implementation22 Jul 2023 Yuwei Yin, Yazheng Yang, Jian Yang, Qi Liu

To tackle these issues, we propose FinPT and FinBench: the former is a novel approach for financial risk prediction that conduct Profile Tuning on large pretrained foundation models, and the latter is a set of high-quality datasets on financial risks such as default, fraud, and churn.

KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation

1 code implementation27 Jun 2023 Jiaqi Bai, Zhao Yan, Jian Yang, Xinnian Liang, Hongcheng Guo, Zhoujun Li

We propose Knowledgeable Prefix Tuning (KnowPrefix-Tuning), a two-stage tuning framework, bypassing the retrieval process in a knowledge-grounded conversation system by injecting prior knowledge into the lightweight knowledge prefix.

Dialogue Generation Response Generation +1

Learnable Differencing Center for Nighttime Depth Perception

no code implementations26 Jun 2023 Zhiqiang Yan, Yupeng Zheng, Chongyi Li, Jun Li, Jian Yang

Depth completion is the task of recovering dense depth maps from sparse ones, usually with the help of color images.

Depth Completion Depth Estimation

Hyperbolic Graph Diffusion Model

1 code implementation13 Jun 2023 Lingfeng Wen, Xuan Tang, Mingjie Ouyang, Xiangxiang Shen, Jian Yang, Daxin Zhu, Mingsong Chen, Xian Wei

In order to simultaneously utilize the data generation capabilities of diffusion models and the ability of hyperbolic embeddings to extract latent hierarchical distributions, we propose a novel graph generation method called, Hyperbolic Graph Diffusion Model (HGDM), which consists of an auto-encoder to encode nodes into successive hyperbolic embeddings, and a DM that operates in the hyperbolic latent space.

Graph Generation

Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image

no code implementations8 Jun 2023 Kun Wang, Zhiqiang Yan, Zhenyu Zhang, Xiang Li, Jun Li, Jian Yang

Our key contributions are: (1) We parameterize the geometry and appearance of the object using a multi-scale global feature extractor, which avoids frequent point-wise feature retrieval and camera dependency.

Contrastive Learning Object +1

Fine-Grained Visual Prompting

1 code implementation NeurIPS 2023 Lingfeng Yang, Yueze Wang, Xiang Li, Xinlong Wang, Jian Yang

Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest.

Visual Prompting

GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking

no code implementations29 May 2023 Jiaqi Bai, Hongcheng Guo, Jiaheng Liu, Jian Yang, Xinnian Liang, Zhao Yan, Zhoujun Li

However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i. e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer.

Answer Generation Dialogue Generation +6

Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?

1 code implementation22 May 2023 Zheng Li, YuXuan Li, Penghai Zhao, RenJie Song, Xiang Li, Jian Yang

Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images.

Data-free Knowledge Distillation

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

1 code implementation CVPR 2023 Yaqi Shen, Le Hui, Jin Xie, Jian Yang

In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds.

Scene Flow Estimation

Refined Response Distillation for Class-Incremental Player Detection

no code implementations1 May 2023 Liang Bai, Hangjie Yuan, Tao Feng, Hong Song, Jian Yang

Furthermore, we present the NBA-IOD and Volleyball-IOD datasets as the benchmark and investigate the IOD tasks of the players systematically.

Knowledge Distillation object-detection +1

Group Equivariant BEV for 3D Object Detection

no code implementations26 Apr 2023 Hongwei Liu, Jian Yang, Jianfeng Zhang, Dongheng Shao, Jielong Guo, Shaobo Li, Xuan Tang, Xian Wei

Experimental results demonstrate that GeqBevNet can extract more rotational equivariant features in the 3D object detection of the actual road scene and improve the performance of object orientation prediction.

3D Object Detection Object +2

Enhancing Large Language Model with Self-Controlled Memory Framework

1 code implementation26 Apr 2023 Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.

Document Summarization Instruction Following +4

Partition-based Stability of Coalitional Games

no code implementations20 Apr 2023 Jian Yang

For the resulting strong, medium, and weak stability concepts, the first is core-compatible in that the traditional core exactly contains those allocations that are associated through this strong stability concept with the all-consolidated partition consisting of only the grand coalition.

Blocking

Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations

no code implementations16 Apr 2023 Jianzhang Zheng, Hao Shen, Jian Yang, Xuan Tang, Mingsong Chen, Hui Yu, Jielong Guo, Xian Wei

Motivated by the important role of ID, in this paper, we propose a novel deep representation learning approach with autoencoder, which incorporates regularization of the global and local ID constraints into the reconstruction of data representations.

Image Classification Representation Learning

Curricular Object Manipulation in LiDAR-based Object Detection

1 code implementation CVPR 2023 Ziyue Zhu, Qiang Meng, Xiao Wang, Ke Wang, Liujiang Yan, Jian Yang

For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages.

3D Object Detection Object +1

Robust Outlier Rejection for 3D Registration with Variational Bayes

1 code implementation CVPR 2023 Haobo Jiang, Zheng Dang, Zhen Wei, Jin Xie, Jian Yang, Mathieu Salzmann

Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.

Bayesian Inference

StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing

1 code implementation28 Mar 2023 Senmao Li, Joost Van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang

A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.

Text-based Image Editing

3D-Aware Multi-Class Image-to-Image Translation with NeRFs

1 code implementation CVPR 2023 Senmao Li, Joost Van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang

In the second step, based on the well-trained multi-class 3D-aware GAN architecture, that preserves view-consistency, we construct a 3D-aware I2I translation system.

Image-to-Image Translation Translation

A Survey of Historical Learning: Learning Models with Learning History

1 code implementation23 Mar 2023 Xiang Li, Ge Wu, Lingfeng Yang, Wenhai Wang, RenJie Song, Jian Yang

The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models.

Ensemble Learning

Large Selective Kernel Network for Remote Sensing Object Detection

1 code implementation ICCV 2023 YuXuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng, Jian Yang, Xiang Li

To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection.

Object object-detection +3

AutoOptLib: Tailoring Metaheuristic Optimizers via Automated Algorithm Design

1 code implementation12 Mar 2023 Qi Zhao, Bai Yan, Taiwei Hu, Xianglong Chen, Qiqi Duan, Jian Yang, Yuhui Shi

In response, this paper proposes AutoOptLib, the first platform for accessible automated design of metaheuristic optimizers.

Metaheuristic Optimization

Non-aligned supervision for Real Image Dehazing

no code implementations8 Mar 2023 Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li, Jian Yang

In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network.

Image Dehazing

Heterogeneous Social Event Detection via Hyperbolic Graph Representations

1 code implementation20 Feb 2023 Zitai Qiu, Jia Wu, Jian Yang, Xing Su, Charu C. Aggarwal

This model addresses the heterogeneity of social media, and, with this graph, the information in social media can be used to capture structural information based on the properties of hyperbolic space.

Contrastive Learning Event Detection

Structure Flow-Guided Network for Real Depth Super-Resolution

no code implementations31 Jan 2023 Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li, Jian Yang

Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).

Depth Estimation Depth Prediction +1

Recurrent Structure Attention Guidance for Depth Super-Resolution

no code implementations31 Jan 2023 Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li, Jian Yang

Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.

Depth Estimation Super-Resolution

State of the Art and Potentialities of Graph-level Learning

no code implementations14 Jan 2023 Zhenyu Yang, Ge Zhang, Jia Wu, Jian Yang, Quan Z. Sheng, Shan Xue, Chuan Zhou, Charu Aggarwal, Hao Peng, Wenbin Hu, Edwin Hancock, Pietro Liò

Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures.

Graph Learning

Multilingual Entity and Relation Extraction from Unified to Language-specific Training

no code implementations11 Jan 2023 Zixiang Wang, Jian Yang, Tongliang Li, Jiaheng Liu, Ying Mo, Jiaqi Bai, Longtao He, Zhoujun Li

In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages.

Relation Relation Extraction +1

Efficient LiDAR Point Cloud Oversegmentation Network

no code implementations ICCV 2023 Le Hui, Linghua Tang, Yuchao Dai, Jin Xie, Jian Yang

Then, to generate homogeneous superpoints from the sparse LiDAR point cloud, we propose a LiDAR point grouping algorithm that simultaneously considers the similarity of point embeddings and the Euclidean distance of points in 3D space.

LIDAR Semantic Segmentation Semantic Segmentation

Few-shot Continual Infomax Learning

no code implementations ICCV 2023 Ziqi Gu, Chunyan Xu, Jian Yang, Zhen Cui

Further, considering that the learned knowledge in the human brain is a generalization of actual information and exists in a certain relational structure, we perform continual structure infomax learning to relieve the catastrophic forgetting problem in the continual learning process.

Continual Learning Few-Shot Learning

Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation

no code implementations ICCV 2023 Haobo Jiang, Zheng Dang, Shuo Gu, Jin Xie, Mathieu Salzmann, Jian Yang

Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.

6D Pose Estimation using RGB Object +2

Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields

no code implementations CVPR 2023 Kangkan Wang, Guofeng Zhang, Suxu Cong, Jian Yang

Previous methods capture the performance of full humans with a personalized template or recover the garments from a single frame with static human poses.

Revisiting the P3P Problem

1 code implementation CVPR 2023 Yaqing Ding, Jian Yang, Viktor Larsson, Carl Olsson, Kalle Åström

One of the classical multi-view geometry problems is the so called P3P problem, where the absolute pose of a calibrated camera is determined from three 2D-to-3D correspondences.

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network

no code implementations29 Dec 2022 Wenjie Li, Juncheng Li, Guangwei Gao, Weihong Deng, Jian Yang, Guo-Jun Qi, Chia-Wen Lin

Recently, great progress has been made in single-image super-resolution (SISR) based on deep learning technology.

Image Super-Resolution

Robust Consensus Clustering and its Applications for Advertising Forecasting

no code implementations27 Dec 2022 Deguang Kong, Miao Lu, Konstantin Shmakov, Jian Yang

Consensus clustering aggregates partitions in order to find a better fit by reconciling clustering results from different sources/executions.

Clustering

Do not Waste Money on Advertising Spend: Bid Recommendation via Concavity Changes

no code implementations26 Dec 2022 Deguang Kong, Konstantin Shmakov, Jian Yang

In computational advertising, a challenging problem is how to recommend the bid for advertisers to achieve the best return on investment (ROI) given budget constraint.

Demystifying Advertising Campaign Bid Recommendation: A Constraint target CPA Goal Optimization

no code implementations26 Dec 2022 Deguang Kong, Konstantin Shmakov, Jian Yang

In cost-per-click (CPC) or cost-per-impression (CPM) advertising campaigns, advertisers always run the risk of spending the budget without getting enough conversions.

Mining User-aware Multi-relations for Fake News Detection in Large Scale Online Social Networks

1 code implementation21 Dec 2022 Xing Su, Jian Yang, Jia Wu, Yuchen Zhang

In this paper, we construct a dual-layer graph (i. e., the news layer and the user layer) to extract multiple relations of news and users in social networks to derive rich information for detecting fake news.

Fake News Detection

GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator

1 code implementation20 Dec 2022 Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li

Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model.

Denoising Sentence +1

One-Stage Cascade Refinement Networks for Infrared Small Target Detection

1 code implementation16 Dec 2022 Yimian Dai, Xiang Li, Fei Zhou, Yulei Qian, Yaohong Chen, Jian Yang

Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection.

Feature Aggregation and Propagation Network for Camouflaged Object Detection

1 code implementation2 Dec 2022 Tao Zhou, Yi Zhou, Chen Gong, Jian Yang, Yu Zhang

In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection.

Object object-detection +1

Curriculum Temperature for Knowledge Distillation

1 code implementation29 Nov 2022 Zheng Li, Xiang Li, Lingfeng Yang, Borui Zhao, RenJie Song, Lei Luo, Jun Li, Jian Yang

In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature.

Image Classification Knowledge Distillation

DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion

no code implementations20 Nov 2022 Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Jun Li, Jian Yang

Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation.

Depth Completion Depth Estimation +2

LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation

no code implementations19 Oct 2022 Hongcheng Guo, Jiaheng Liu, Haoyang Huang, Jian Yang, Zhoujun Li, Dongdong Zhang, Zheng Cui, Furu Wei

To this end, we first propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.

Multimodal Machine Translation Translation

DAGAD: Data Augmentation for Graph Anomaly Detection

1 code implementation18 Oct 2022 Fanzhen Liu, Xiaoxiao Ma, Jia Wu, Jian Yang, Shan Xue, Amin Beheshti, Chuan Zhou, Hao Peng, Quan Z. Sheng, Charu C. Aggarwal

To bridge the gaps, this paper devises a novel Data Augmentation-based Graph Anomaly Detection (DAGAD) framework for attributed graphs, equipped with three specially designed modules: 1) an information fusion module employing graph neural network encoders to learn representations, 2) a graph data augmentation module that fertilizes the training set with generated samples, and 3) an imbalance-tailored learning module to discriminate the distributions of the minority (anomalous) and majority (normal) classes.

Data Augmentation Graph Anomaly Detection

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval

4 code implementations28 Sep 2022 Yang shen, Xuhao Sun, Xiu-Shen Wei, Qing-Yuan Jiang, Jian Yang

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks.

Image Retrieval Retrieval

Spatio-Temporal Relation Learning for Video Anomaly Detection

no code implementations27 Sep 2022 Hui Lv, Zhen Cui, Biao Wang, Jian Yang

Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly.

Anomaly Detection Knowledge Graph Embedding +5

Grouped Adaptive Loss Weighting for Person Search

no code implementations23 Sep 2022 Yanling Tian, Di Chen, Yunan Liu, Shanshan Zhang, Jian Yang

A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates.

Model Optimization Multi-Task Learning +2

Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking

no code implementations14 Sep 2022 Haobo Jiang, Kaihao Lan, Le Hui, Guangyu Li, Jin Xie, Jian Yang

The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization.

Object Localization Object Tracking +1

LogLG: Weakly Supervised Log Anomaly Detection via Log-Event Graph Construction

no code implementations23 Aug 2022 Hongcheng Guo, Yuhui Guo, Renjie Chen, Jian Yang, Jiaheng Liu, Zhoujun Li, Tieqiao Zheng, Weichao Hou, Liangfan Zheng, Bo Zhang

Experiments on five benchmarks validate the effectiveness of LogLG for detecting anomalies on unlabeled log data and demonstrate that LogLG, as the state-of-the-art weakly supervised method, achieves significant performance improvements compared to existing methods.

Anomaly Detection graph construction +1

GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation

1 code implementation29 Jul 2022 Jian Yang, Yuwei Yin, Liqun Yang, Shuming Ma, Haoyang Huang, Dongdong Zhang, Furu Wei, Zhoujun Li

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation.

Machine Translation Translation

RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

1 code implementation25 Jul 2022 Mu He, Le Hui, Yikai Bian, Jian Ren, Jin Xie, Jian Yang

In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth.

Data Augmentation Monocular Depth Estimation

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

1 code implementation25 Jul 2022 Le Hui, Lingpeng Wang, Linghua Tang, Kaihao Lan, Jin Xie, Jian Yang

Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.

3D Single Object Tracking Object Tracking

HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation

1 code implementation11 Jul 2022 Jian Yang, Yuwei Yin, Shuming Ma, Dongdong Zhang, Zhoujun Li, Furu Wei

Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages.

Machine Translation Translation

GCN-based Multi-task Representation Learning for Anomaly Detection in Attributed Networks

no code implementations8 Jul 2022 Venus Haghighi, Behnaz Soltani, Adnan Mahmood, Quan Z. Sheng, Jian Yang

Anomaly detection in attributed networks has received a considerable attention in recent years due to its applications in a wide range of domains such as finance, network security, and medicine.

Anomaly Detection Community Detection +2

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

1 code implementation6 Jul 2022 Wenjie Li, Juncheng Li, Guangwei Gao, Jiantao Zhou, Jian Yang, Guo-Jun Qi

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction.

Image Super-Resolution

Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels

no code implementations27 Jun 2022 Chuang Zhang, Li Shen, Jian Yang, Chen Gong

To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels.

Learning with noisy labels Memorization

Graph-level Neural Networks: Current Progress and Future Directions

no code implementations31 May 2022 Ge Zhang, Jia Wu, Jian Yang, Shan Xue, Wenbin Hu, Chuan Zhou, Hao Peng, Quan Z. Sheng, Charu Aggarwal

To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.

Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality

1 code implementation20 May 2022 Xiang Li, Wenhai Wang, Lingfeng Yang, Jian Yang

Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy.

Object Detection

Bi-level Alignment for Cross-Domain Crowd Counting

1 code implementation CVPR 2022 Shenjian Gong, Shanshan Zhang, Jian Yang, Dengxin Dai, Bernt Schiele

The main challenge for this task is to achieve high-quality manual annotations on a large amount of training data.

AutoML Crowd Counting +2

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

no code implementations11 May 2022 Wentao Yu, Sheng Wan, Guangyu Li, Jian Yang, Chen Gong

To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed Contrastive Graph Convolutional Network (ConGCN), for HSI classification.

Classification Contrastive Learning +2

Semantics-Guided Moving Object Segmentation with 3D LiDAR

no code implementations6 May 2022 Shuo Gu, Suling Yao, Jian Yang, Hui Kong

Instead of segmenting the moving objects directly, the network conducts single-scan-based semantic segmentation and multiple-scan-based moving object segmentation in turn.

Object Segmentation +1

Towards Explainable Meta-Learning for DDoS Detection

no code implementations5 Apr 2022 Qianru Zhou, Rongzhen Li, Lei Xu, Arumugam Nallanathan, Jian Yang, Anmin Fu

With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more.

Intrusion Detection Meta-Learning

OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation

no code implementations28 Mar 2022 Jianjun Qian, Shumin Zhu, Chaoyu Zhao, Jian Yang, Wai Keung Wong

To this end, some deep convolutional neural networks (CNNs) have been developed to learn discriminative feature by designing properly margin-based losses, which perform well on easy samples but fail on hard samples.

Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation

1 code implementation CVPR 2022 Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang

Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.

Style Transfer

Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks

1 code implementation22 Mar 2022 Haobo Jiang, Jin Xie, Jian Yang

Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.

Q-Learning

Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion

no code implementations18 Mar 2022 Zhiqiang Yan, Xiang Li, Kun Wang, Zhenyu Zhang, Jun Li, Jian Yang

To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.

Depth Completion Transfer Learning

RecursiveMix: Mixed Learning with History

1 code implementation14 Mar 2022 Lingfeng Yang, Xiang Li, Borui Zhao, RenJie Song, Jian Yang

In semantic segmentation, RM also surpasses the baseline and CutMix by 1. 9 and 1. 1 mIoU points under UperNet on ADE20K, respectively.

object-detection Object Detection +1

Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information

1 code implementation CVPR 2022 Lingfeng Yang, Xiang Li, RenJie Song, Borui Zhao, Juntian Tao, Shihao Zhou, Jiajun Liang, Jian Yang

Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.

Fine-Grained Image Classification

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

1 code implementation23 Feb 2022 Yaqi Shen, Le Hui, Haobo Jiang, Jin Xie, Jian Yang

In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration.

Model Optimization Point Cloud Registration

Webly-Supervised Fine-Grained Recognition with Partial Label Learning

1 code implementation IJCAI 2022 Yu-Yan Xu, Yang shen, Xiu-Shen Wei, Jian Yang

The task of webly-supervised fne-grained recognition is to boost recognition accuracy of classifying subordinate categories (e. g., different bird species)by utilizing freely available but noisy web data. As the label noises signifcantly hurt the network training, it is desirable to distinguish and eliminate noisy images.

Partial Label Learning

PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation

no code implementations COLING 2022 Juncheng Wan, Jian Yang, Shuming Ma, Dongdong Zhang, Weinan Zhang, Yong Yu, Zhoujun Li

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable.

Machine Translation NMT +1

Synthesizing Tensor Transformations for Visual Self-attention

no code implementations5 Jan 2022 Xian Wei, Xihao Wang, Hai Lan, JiaMing Lei, Yanhui Huang, Hui Yu, Jian Yang

Self-attention shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning.

Image Captioning Image Classification

SMDT: Selective Memory-Augmented Neural Document Translation

no code implementations5 Jan 2022 Xu Zhang, Jian Yang, Haoyang Huang, Shuming Ma, Dongdong Zhang, Jinlong Li, Furu Wei

Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation.

Document Level Machine Translation Document Translation +4

CVNet: Contour Vibration Network for Building Extraction

1 code implementation CVPR 2022 Ziqiang Xu, Chunyan Xu, Zhen Cui, Xiangwei Zheng, Jian Yang

The classic active contour model raises a great promising solution to polygon-based object extraction with the progress of deep learning recently.

Model Optimization

Relative Pose From a Calibrated and an Uncalibrated Smartphone Image

no code implementations CVPR 2022 Yaqing Ding, Daniel Barath, Jian Yang, Zuzana Kukelova

In this paper, we propose a new minimal and a non-minimal solver for estimating the relative camera pose together with the unknown focal length of the second camera.

A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos

no code implementations CVPR 2022 Hanyu Xuan, Zhiliang Wu, Jian Yang, Yan Yan, Xavier Alameda-Pineda

Humans can easily recognize where and how the sound is produced via watching a scene and listening to corresponding audio cues.

Multiple Instance Learning

TransLog: A Unified Transformer-based Framework for Log Anomaly Detection

no code implementations31 Dec 2021 Hongcheng Guo, Xingyu Lin, Jian Yang, Yi Zhuang, Jiaqi Bai, Tieqiao Zheng, Bo Zhang, Zhoujun Li

Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage.

Anomaly Detection

A$^2$-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval

1 code implementation NeurIPS 2021 Xiu-Shen Wei, Yang shen, Xuhao Sun, Han-Jia Ye, Jian Yang

Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations.

Attribute Image Retrieval +1

Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation

no code implementations NeurIPS 2021 Yunan Liu, Shanshan Zhang, Yang Li, Jian Yang

In this setting, we embed an additional pair of “latent-latent” to reduce the domain gap between the source and different latent domains, allowing the model to adapt well on multiple target domains simultaneously.

Domain Adaptation Meta-Learning +1

Universal Semi-Supervised Learning

no code implementations NeurIPS 2021 Zhuo Huang, Chao Xue, Bo Han, Jian Yang, Chen Gong

Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i. e., class set) and feature distribution (i. e., feature domain) are different between labeled dataset and unlabeled dataset.

Domain Adaptation

Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution

no code implementations17 Nov 2021 Xi Cheng, Jun Li, Qiang Dai, ZhenYong Fu, Jian Yang

In our SF-SIM, we propose a noise estimator which can effectively suppress the noise in the image and enable our method to work under the low light and short exposure environment, without the need for stacking multiple frames for non-local denoising.

Denoising Super-Resolution

Keypoint Message Passing for Video-based Person Re-Identification

1 code implementation16 Nov 2021 Di Chen, Andreas Doering, Shanshan Zhang, Jian Yang, Juergen Gall, Bernt Schiele

Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras.

Representation Learning Video-Based Person Re-Identification

Fine-Grained Image Analysis with Deep Learning: A Survey

no code implementations11 Nov 2021 Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, Serge Belongie

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.

Fine-Grained Image Recognition Image Retrieval +1

3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds

1 code implementation NeurIPS 2021 Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie, Jian Yang

The Siamese shape-aware feature learning network can capture 3D shape information of the object to learn the discriminative features of the object so that the potential target from the background in sparse point clouds can be identified.

3D Object Tracking Object Tracking

Neural BRDFs: Representation and Operations

no code implementations6 Nov 2021 Jiahui Fan, Beibei Wang, Miloš Hašan, Jian Yang, Ling-Qi Yan

Bidirectional reflectance distribution functions (BRDFs) are pervasively used in computer graphics to produce realistic physically-based appearance.

Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning

no code implementations22 Oct 2021 Yang Yang, Hongchen Wei, HengShu Zhu, dianhai yu, Hui Xiong, Jian Yang

In detail, considering that the heterogeneous gap between modalities always leads to the supervision difficulty of using the global embedding directly, CPRC turns to transform both the raw image and corresponding generated sentence into the shared semantic space, and measure the generated sentence from two aspects: 1) Prediction consistency.

Image Captioning Informativeness +2

A Survey of Knowledge Enhanced Pre-trained Models

no code implementations1 Oct 2021 Jian Yang, Xinyu Hu, Gang Xiao, Yulong Shen

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning.

Logical Reasoning Representation Learning +1

Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation

no code implementations1 Oct 2021 Zheng Li, Xiang Li, Lingfeng Yang, Jian Yang, Zhigeng Pan

Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm.

Self-Knowledge Distillation

Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

1 code implementation ICCV 2021 Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian, Jian Yang

Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.

Point Cloud Registration

FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation

1 code implementation2 Sep 2021 Guangwei Gao, Guoan Xu, Juncheng Li, Yi Yu, Huimin Lu, Jian Yang

Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch.

Autonomous Driving Drone navigation +1

Learning Fair Face Representation With Progressive Cross Transformer

no code implementations11 Aug 2021 Yong Li, Yufei Sun, Zhen Cui, Shiguang Shan, Jian Yang

To mitigate racial bias and meantime preserve robust FR, we abstract face identity-related representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition.

Denoising Face Recognition

Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration

no code implementations5 Aug 2021 Haobo Jiang, Jin Xie, Jianjun Qian, Jian Yang

By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network.

Point Cloud Registration

Multilingual Agreement for Multilingual Neural Machine Translation

no code implementations ACL 2021 Jian Yang, Yuwei Yin, Shuming Ma, Haoyang Huang, Dongdong Zhang, Zhoujun Li, Furu Wei

Although multilingual neural machine translation (MNMT) enables multiple language translations, the training process is based on independent multilingual objectives.

Machine Translation Translation

RigNet: Repetitive Image Guided Network for Depth Completion

no code implementations29 Jul 2021 Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Jun Li, Jian Yang

However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.

Depth Completion Depth Estimation +1

Graph Jigsaw Learning for Cartoon Face Recognition

1 code implementation14 Jul 2021 Yong Li, Lingjie Lao, Zhen Cui, Shiguang Shan, Jian Yang

To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner.

Classification Face Recognition

A Comprehensive Survey on Graph Anomaly Detection with Deep Learning

1 code implementation14 Jun 2021 Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z. Sheng, Hui Xiong, Leman Akoglu

In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection.

Graph Anomaly Detection

dFDA-VeD: A Dynamic Future Demand Aware Vehicle Dispatching System

no code implementations10 Jun 2021 Yang Guo, Tarique Anwar, Jian Yang, Jia Wu

As the process should be socially and economically profitable, the task of vehicle dispatching is highly challenging, specially due to the time-varying travel demands and traffic conditions.

Smart-Start Decoding for Neural Machine Translation

no code implementations NAACL 2021 Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou

Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left.

Machine Translation Translation

Robotic Brain Storm Optimization: A Multi-target Collaborative Searching Paradigm for Swarm Robotics

no code implementations27 May 2021 Jian Yang, Yuhui Shi

Swarm intelligence optimization algorithms can be adopted in swarm robotics for target searching tasks in a 2-D or 3-D space by treating the target signal strength as fitness values.

Clustering

Attention-oriented Brain Storm Optimization for Multimodal Optimization Problems

1 code implementation27 May 2021 Jian Yang, Yuhui Shi

Rather than converge to a single global optimum, the proposed method can guide the search procedure to converge to multiple "salient" solutions.

Clustering

A Comprehensive Survey on Community Detection with Deep Learning

no code implementations26 May 2021 Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu

A community reveals the features and connections of its members that are different from those in other communities in a network.

Clustering Community Detection +3

DONet: Dual-Octave Network for Fast MR Image Reconstruction

no code implementations12 May 2021 Chun-Mei Feng, Zhanyuan Yang, Huazhu Fu, Yong Xu, Jian Yang, Ling Shao

In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data, for fast parallel MR image reconstruction.

Image Reconstruction

Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks

1 code implementation3 May 2021 Haobo Jiang, Jin Xie, Jian Yang

Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.

Q-Learning

SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network

1 code implementation16 Apr 2021 Mingmei Cheng, Le Hui, Jin Xie, Jian Yang

In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points.

Point Cloud Segmentation Scene Understanding +2

Learning Normal Dynamics in Videos with Meta Prototype Network

1 code implementation CVPR 2021 Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, Jian Yang

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection.

Anomaly Detection Meta-Learning +1

Contrastive Embedding for Generalized Zero-Shot Learning

3 code implementations CVPR 2021 Zongyan Han, ZhenYong Fu, Shuo Chen, Jian Yang

To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework.

Generalized Zero-Shot Learning

Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition

no code implementations25 Mar 2021 Guangwei Gao, Yi Yu, Jian Yang, Guo-Jun Qi, Meng Yang

(i) To learn more robust and discriminative features, we desire to adaptively fuse the contextual features from different layers.

Face Recognition Representation Learning

JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

no code implementations25 Mar 2021 Guangwei Gao, Lei Tang, Fei Wu, Huimin Lu, Jian Yang

In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.

Denoising Super-Resolution

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

no code implementations24 Mar 2021 Guangwei Gao, Guoan Xu, Yi Yu, Jin Xie, Jian Yang, Dong Yue

In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones.

Autonomous Driving Real-Time Semantic Segmentation +1

Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction

no code implementations10 Mar 2021 Xuran Xu, Tong Zhang, Chunyan Xu, Zhen Cui, Jian Yang

We further extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data.

Management Tensor Decomposition +1

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

1 code implementation14 Jan 2021 Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu, Jian Yang, Chen Gong

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs).

Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition

1 code implementation7 Jan 2021 Le Hui, Mingmei Cheng, Jin Xie, Jian Yang

In this paper, we develop an efficient point cloud learning network (EPC-Net) to form a global descriptor for visual place recognition, which can obtain good performance and reduce computation memory and inference time.

Point Cloud Retrieval Retrieval +1

Scribble-Supervised Semantic Segmentation Inference

no code implementations ICCV 2021 Jingshan Xu, Chuanwei Zhou, Zhen Cui, Chunyan Xu, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang

In this paper, we propose a progressive segmentation inference (PSI) framework to tackle with scribble-supervised semantic segmentation.

Segmentation Semantic Segmentation

Superpoint Network for Point Cloud Oversegmentation

1 code implementation ICCV 2021 Le Hui, Jia Yuan, Mingmei Cheng, Jin Xie, Xiaoya Zhang, Jian Yang

Specifically, in our clustering network, we first jointly learn a soft point-superpoint association map from the coordinate and feature spaces of point clouds, where each point is assigned to the superpoint with a learned weight.

Clustering Semantic Segmentation

Graph Deformer Network

no code implementations1 Jan 2021 Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang, Jian Yang, Wei Liu

In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.

Isomorphism Testing

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

1 code implementation ICCV 2021 Le Hui, Hang Yang, Mingmei Cheng, Jin Xie, Jian Yang

In order to obtain discriminative global descriptors, we construct a pyramid VLAD module to aggregate the multi-scale feature maps of point clouds into the global descriptors.

3D Place Recognition Point Cloud Retrieval +1

Wasserstein Coupled Graph Learning for Cross-Modal Retrieval

no code implementations ICCV 2021 Yun Wang, Tong Zhang, Xueya Zhang, Zhen Cui, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jian Yang

Then, a Wasserstein coupled dictionary, containing multiple pairs of counterpart graph keys with each key corresponding to one modality, is constructed for further feature learning.

Cross-Modal Retrieval Graph Embedding +2

Globally Optimal Relative Pose Estimation with Gravity Prior

no code implementations CVPR 2021 Yaqing Ding, Daniel Barath, Jian Yang, Hui Kong, Zuzana Kukelova

Smartphones, tablets and camera systems used, e. g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately.

Pose Estimation

They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning

no code implementations27 Nov 2020 Zhuo Huang, Ying Tai, Chengjie Wang, Jian Yang, Chen Gong

Semi-Supervised Learning (SSL) with mismatched classes deals with the problem that the classes-of-interests in the limited labeled data is only a subset of the classes in massive unlabeled data.

Domain Adaptation

Aspect Based Sentiment Analysis with Self-Attention and Gated Convolutional Networks

no code implementations4 Nov 2020 Jian Yang, Juan Yang

Therefore, to solve the problems above, we build a new model based on gating mechanism, combined with convolutional neural networks (CNN) and self-attention mechanism.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1

Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising

2 code implementations23 Oct 2020 Yali Peng, Yue Cao, Shigang Liu, Jian Yang, WangMeng Zuo

To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance.

Image Denoising

Interest-Behaviour Multiplicative Network for Resource-limited Recommendation

no code implementations24 Sep 2020 Qianliang Wu, Tong Zhang, Zhen Cui, Jian Yang

In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics.

Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification

no code implementations19 Sep 2020 Sheng Wan, Chen Gong, Shirui Pan, Jie Yang, Jian Yang

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.

General Classification graph construction +2

Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning

no code implementations15 Sep 2020 Sheng Wan, Shirui Pan, Jian Yang, Chen Gong

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph.

Frontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration

1 code implementation7 Sep 2020 Zezhou Sun, Banghe Wu, Cheng-Zhong Xu, Sanjay E. Sarma, Jian Yang, Hui Kong

We propose an integrated approach to active exploration by exploiting the Cartographer method as the base SLAM module for submap creation and performing efficient frontier detection in the geometrically co-aligned submaps induced by graph optimization.

Spatial Transformer Point Convolution

no code implementations3 Sep 2020 Yuan Fang, Chunyan Xu, Zhen Cui, Yuan Zong, Jian Yang

In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds.

Dictionary Learning Semantic Segmentation

Learning Adaptive Embedding Considering Incremental Class

1 code implementation31 Aug 2020 Yang Yang, Zhen-Qiang Sun, HengShu Zhu, Yanjie Fu, Hui Xiong, Jian Yang

To this end, we propose a Class-Incremental Learning without Forgetting (CILF) framework, which aims to learn adaptive embedding for processing novel class detection and model update in a unified framework.

Class Incremental Learning Clustering +1

ICS-Assist: Intelligent Customer Inquiry Resolution Recommendation in Online Customer Service for Large E-Commerce Businesses

no code implementations22 Aug 2020 Min Fu, Jiwei Guan, Xi Zheng, Jie zhou, Jianchao Lu, Tianyi Zhang, Shoujie Zhuo, Lijun Zhan, Jian Yang

Existing solution recommendation methods for online customer service are unable to determine the best solutions at runtime, leading to poor satisfaction of end customers.

Localizing Anomalies from Weakly-Labeled Videos

1 code implementation20 Aug 2020 Hui Lv, Chuanwei Zhou, Chunyan Xu, Zhen Cui, Jian Yang

In addition, in order to fully utilize the spatial context information, the immediate semantics are directly derived from the segment representations.

Anomaly Detection In Surveillance Videos Video Anomaly Detection

Instance-Aware Graph Convolutional Network for Multi-Label Classification

no code implementations19 Aug 2020 Yun Wang, Tong Zhang, Zhen Cui, Chunyan Xu, Jian Yang

For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model.

Classification General Classification +2

S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification

no code implementations11 Aug 2020 Yang Yang, Zhen-Qiang Sun, Hui Xiong, Jian Yang

Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time.

General Classification Knowledge Distillation +1

Graph Wasserstein Correlation Analysis for Movie Retrieval

no code implementations ECCV 2020 Xueya Zhang, Tong Zhang, Xiaobin Hong, Zhen Cui, Jian Yang

Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning.

Metric Learning Retrieval

Progressive Point Cloud Deconvolution Generation Network

1 code implementation ECCV 2020 Le Hui, Rui Xu, Jin Xie, Jianjun Qian, Jian Yang

Starting from the low-resolution point clouds, with the bilateral interpolation and max-pooling operations, the deconvolution network can progressively output high-resolution local and global feature maps.

Point Cloud Generation

Improving Neural Machine Translation with Soft Template Prediction

no code implementations ACL 2020 Jian Yang, Shuming Ma, Dong-dong Zhang, Zhoujun Li, Ming Zhou

Although neural machine translation (NMT) has achieved significant progress in recent years, most previous NMT models only depend on the source text to generate translation.

Machine Translation NMT +1

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

no code implementations CVPR 2020 Zongyan Han, Zhen-Yong Fu, Jian Yang

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species.

Generalized Zero-Shot Learning Object +1

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

7 code implementations NeurIPS 2020 Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang

Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.

Dense Object Detection General Classification

Deep Learning for Community Detection: Progress, Challenges and Opportunities

1 code implementation17 May 2020 Fanzhen Liu, Shan Xue, Jia Wu, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Jian Yang, Philip S. Yu

As communities represent similar opinions, similar functions, similar purposes, etc., community detection is an important and extremely useful tool in both scientific inquiry and data analytics.

Clustering Community Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.