Search Results for author: Yong liu

Found 225 papers, 73 papers with code

Toward Knowledge-Enriched Conversational Recommendation Systems

no code implementations NLP4ConvAI (ACL) 2022 Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.

Knowledge Graphs Recommendation Systems +1

Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging

no code implementations23 Mar 2023 Meng Wang, Lianyu Wang, Xinxing Xu, Ke Zou, Yiming Qian, Rick Siow Mong Goh, Yong liu, Huazhu Fu

Our TWEU employs an evidential deep layer to produce the uncertainty score with the DR staging results for client reliability evaluation.

Federated Learning

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

no code implementations16 Mar 2023 Kunyang Han, Yong liu, Jun Hao Liew, Henghui Ding, Yunchao Wei, Jiajun Liu, Yitong Wang, Yansong Tang, Yujiu Yang, Jiashi Feng, Yao Zhao

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS).

Knowledge Distillation Open Vocabulary Semantic Segmentation +3

Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment

no code implementations14 Mar 2023 Zhihao Chen, Yang Zhou, Anh Tran, Junting Zhao, Liang Wan, Gideon Ooi, Lionel Cheng, Choon Hua Thng, Xinxing Xu, Yong liu, Huazhu Fu

To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo).

Phrase Grounding Visual Grounding

A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation

no code implementations28 Feb 2023 Lin Li, Wendong Ding, Yongkun Wen, Yufei Liang, Yong liu, Guowei Wan

For overlap detection, a cross-attention module is applied for interacting contextual information of input point clouds, followed by a classification head to estimate the overlapping region.

Point Cloud Registration

Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK

no code implementations16 Feb 2023 Xiongtao Zhang, Zezong Yin, Yunliang Jiang, Yizhang Jiang, Danfeng Sun, Yong liu

High-order Takagi-Sugeno-Kang (TSK) fuzzy classifiers possess powerful classification performance yet have fewer fuzzy rules, but always be impaired by its exponential growth training time and poorer interpretability owing to High-order polynomial used in consequent part of fuzzy rule, while Low-order TSK fuzzy classifiers run quickly with high interpretability, however they usually require more fuzzy rules and perform relatively not very well.

Benchmarking Knowledge Distillation

TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation

no code implementations16 Feb 2023 Yunliang Jiang, Lili Yan, Xiongtao Zhang, Yong liu, Danfeng Sun

One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention.

Image Harmonization Image Super-Resolution

Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning

1 code implementation14 Feb 2023 Shanqi Liu, Yujing Hu, Runze Wu, Dong Xing, Yu Xiong, Changjie Fan, Kun Kuang, Yong liu

We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios.

Multi-agent Reinforcement Learning

Operation-level Progressive Differentiable Architecture Search

1 code implementation11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.

Neural Architecture Search

Improving Differentiable Architecture Search via Self-Distillation

no code implementations11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.

Neural Architecture Search

Learning Discretized Neural Networks under Ricci Flow

no code implementations7 Feb 2023 Jun Chen, Hanwen Chen, Mengmeng Wang, Guang Dai, Yong liu

We propose an analysis that this mismatch can be viewed as a metric perturbation in a Riemannian manifold through the lens of duality theory.

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System

no code implementations2 Feb 2023 Tong Zhang, Yong liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.

IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing

1 code implementation31 Jan 2023 Guoyang Xie, Jinbao Wang, Jiaqi Liu, Jiayi Lyu, Yong liu, Chengjie Wang, Feng Zheng, Yaochu Jin

We realize that the lack of actual IM settings most probably hinders the development and usage of these methods in real-world applications.

Anomaly Detection Continual Learning +1

TrFedDis: Trusted Federated Disentangling Network for Non-IID Domain Feature

1 code implementation30 Jan 2023 Meng Wang, Kai Yu, Chun-Mei Feng, Yiming Qian, Ke Zou, Lianyu Wang, Rick Siow Mong Goh, Xinxing Xu, Yong liu, Huazhu Fu

To the best of our knowledge, our proposed TrFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features.

Federated Learning

FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation

no code implementations20 Jan 2023 Junyu Zhu, Lina Liu, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang

The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods.

Image Reconstruction Monocular Depth Estimation +2

Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition

no code implementations19 Jan 2023 Jiazheng Xing, Mengmeng Wang, Boyu Mu, Yong liu

In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner.

Few-Shot action recognition Few Shot Action Recognition

BSNet: Lane Detection via Draw B-spline Curves Nearby

no code implementations17 Jan 2023 Haoxin Chen, Mengmeng Wang, Yong liu

The locality of lane representation is the ability to modify lanes locally which can simplify parameter optimization.

Lane Detection

Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation

1 code implementation3 Jan 2023 Yue Han, Jiangning Zhang, Zhucun Xue, Chao Xu, Xintian Shen, Yabiao Wang, Chengjie Wang, Yong liu, Xiangtai Li

In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework.

Benchmarking Few-Shot Object Detection +3

Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition

no code implementations9 Dec 2022 Xinzhe Ni, Hao Wen, Yong liu, Yatai Ji, Yujiu Yang

A frozen CLIP text encoder is introduced in the text flow, and a semantic-enhanced module is used to enhance text features.

Few-Shot action recognition Few Shot Action Recognition +1

AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer

no code implementations3 Dec 2022 Tianwei Lin, Honglin Lin, Fu Li, Dongliang He, Wenhao Wu, Meiling Wang, Xin Li, Yong liu

Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair.

Style Transfer

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series

1 code implementation2 Dec 2022 Qianwen Meng, Hangwei Qian, Yong liu, Lizhen Cui, Yonghui Xu, Zhiqi Shen

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting.

Contrastive Learning Representation Learning +1

Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images

1 code implementation1 Dec 2022 Meng Wang, Kai Yu, Chun-Mei Feng, Ke Zou, Yanyu Xu, Qingquan Meng, Rick Siow Mong Goh, Yong liu, Xinxing Xu, Huazhu Fu

Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed.

Inductive Graph Transformer for Delivery Time Estimation

1 code implementation5 Nov 2022 Xin Zhou, Jinglong Wang, Yong liu, Xingyu Wu, Zhiqi Shen, Cyril Leung

Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences.

Global Spectral Filter Memory Network for Video Object Segmentation

1 code implementation11 Oct 2022 Yong liu, Ran Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang

Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head).

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals

no code implementations6 Oct 2022 Chen Li, Xiaoyu Wang, Tongyu Zong, Houwei Cao, Yong liu

Edge caching plays an increasingly important role in boosting user content retrieval performance while reducing redundant network traffic.


TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

1 code implementation5 Oct 2022 Haixu Wu, Tengge Hu, Yong liu, Hang Zhou, Jianmin Wang, Mingsheng Long

TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.

Action Recognition Anomaly Detection +3

Generative Model Watermarking Based on Human Visual System

no code implementations30 Sep 2022 Li Zhang, Yong liu, Shaoteng Liu, Tianshu Yang, Yexin Wang, Xinpeng Zhang, Hanzhou Wu

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.

Mask-Guided Image Person Removal with Data Synthesis

no code implementations29 Sep 2022 Yunliang Jiang, Chenyang Gu, Zhenfeng Xue, Xiongtao Zhang, Yong liu

As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains.

Rethinking Dimensionality Reduction in Grid-based 3D Object Detection

no code implementations20 Sep 2022 Dihe Huang, Ying Chen, Yikang Ding, Jinli Liao, Jianlin Liu, Kai Wu, Qiang Nie, Yong liu, Chengjie Wang, Zhiheng Li

In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.

3D Object Detection Cloud Detection +2

Exemplar-Based Image Colorization with A Learning Framework

no code implementations13 Sep 2022 Zhenfeng Xue, Jiandang Yang, Jie Ren, Yong liu

This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image.

Colorization Image Colorization

Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution

1 code implementation29 Aug 2022 Yifeng Zhou, Chuming Lin, Donghao Luo, Yong liu, Ying Tai, Chengjie Wang, Mingang Chen

Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging.

Blind Super-Resolution Image Super-Resolution +1

ATPL: Mutually enhanced adversarial training and pseudo labeling for unsupervised domain adaptation

no code implementations Knowledge-Based Systems 2022 Changan Yi, Haotian Chen, Yonghui Xu, Yong liu, Lei Jiang, Haishu Tan

Accordingly, ATPL will use the pseudo-labeled information to improve the adversarial training process, which can guarantee the feature transferability by generating adversarial data to fill in the domain gap.

Unsupervised Domain Adaptation

SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud

1 code implementation3 Aug 2022 Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong liu

To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.

Association Point Cloud Registration

DA$^2$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping

no code implementations31 Jul 2022 Guangyao Zhai, Yu Zheng, Ziwei Xu, Xin Kong, Yong liu, Benjamin Busam, Yi Ren, Nassir Navab, Zhengyou Zhang

In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects.

Layer-refined Graph Convolutional Networks for Recommendation

1 code implementation22 Jul 2022 Xin Zhou, Donghui Lin, Yong liu, Chunyan Miao

Specifically, these models usually aggregate all layer embeddings for node updating and achieve their best recommendation performance within a few layers because of over-smoothing.

Adaptive Assignment for Geometry Aware Local Feature Matching

1 code implementation18 Jul 2022 Dihe Huang, Ying Chen, Shang Xu, Yong liu, Wenlong Wu, Yikang Ding, Chengjie Wang, Fan Tang

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance.

E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context

1 code implementation17 Jul 2022 Zizhang Li, Mengmeng Wang, Huaijin Pi, Kechun Xu, Jianbiao Mei, Yong liu

However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance.

Learning Quality-aware Dynamic Memory for Video Object Segmentation

1 code implementation16 Jul 2022 Yong liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, Yujiu Yang

However, they mainly focus on better matching between the current frame and the memory frames without explicitly paying attention to the quality of the memory.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

Bootstrap Latent Representations for Multi-modal Recommendation

1 code implementation13 Jul 2022 Xin Zhou, HongYu Zhou, Yong liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, Feijun Jiang

Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e. g., user-user or item-item relation graph) to augment the learned representations of users and/or items.

Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference

no code implementations29 Jun 2022 Yinan Zhang, Boyang Li, Yong liu, You Yuan, Chunyan Miao

Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.

Reinforcement Learning (RL)

EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm

1 code implementation19 Jun 2022 Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong liu, DaCheng Tao

Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.

Image Classification

Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM

no code implementations6 Jun 2022 Yuzhe Li, Yong liu, Bo Li, Weiping Wang, Nan Liu

In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.

Enhancing Sequential Recommendation with Graph Contrastive Learning

no code implementations30 May 2022 Yixin Zhang, Yong liu, Yonghui Xu, Hao Xiong, Chenyi Lei, wei he, Lizhen Cui, Chunyan Miao

Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.

Auxiliary Learning Contrastive Learning +1

Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting

1 code implementation28 May 2022 Yong liu, Haixu Wu, Jianmin Wang, Mingsheng Long

However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.

Time Series Forecasting

UniInst: Unique Representation for End-to-End Instance Segmentation

1 code implementation25 May 2022 Yimin Ou, Rui Yang, Lufan Ma, Yong liu, Jiangpeng Yan, Shang Xu, Chengjie Wang, Xiu Li

Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e. g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions.

Instance Segmentation Re-Ranking +1

Ridgeless Regression with Random Features

1 code implementation1 May 2022 Jian Li, Yong liu, Yingying Zhang

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.


Understanding the Generalization Performance of Spectral Clustering Algorithms

no code implementations30 Apr 2022 Shaojie Li, Sheng Ouyang, Yong liu

The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance.

Sharper Utility Bounds for Differentially Private Models

no code implementations22 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.

Stability and Generalization of Differentially Private Minimax Problems

no code implementations11 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.

CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow

1 code implementation CVPR 2022 Xiuchao Sui, Shaohua Li, Xue Geng, Yan Wu, Xinxing Xu, Yong liu, Rick Goh, Hongyuan Zhu

This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images.

Optical Flow Estimation

Region-Aware Face Swapping

no code implementations CVPR 2022 Chao Xu, Jiangning Zhang, Miao Hua, Qian He, Zili Yi, Yong liu

This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction.

Face Generation Face Swapping +1

Towards Efficient and Scalable Sharpness-Aware Minimization

1 code implementation CVPR 2022 Yong liu, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, Yang You

Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers.

Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection

1 code implementation1 Mar 2022 Yufei Liang, Jiangning Zhang, Shiwei Zhao, Runze Wu, Yong liu, Shuwen Pan

Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance.

Unsupervised Anomaly Detection

Guide Local Feature Matching by Overlap Estimation

1 code implementation18 Feb 2022 Ying Chen, Dihe Huang, Shang Xu, Jianlin Liu, Yong liu

Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important.

A Survey of Visual Sensory Anomaly Detection

1 code implementation14 Feb 2022 Xi Jiang, Guoyang Xie, Jinbao Wang, Yong liu, Chengjie Wang, Feng Zheng, Yaochu Jin

In this survey, we are the first one to provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.

Anomaly Detection

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

no code implementations12 Jan 2022 Jiangning Zhang, Chao Xu, Jian Li, Yue Han, Yabiao Wang, Ying Tai, Yong liu

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.

Colorization Image Colorization +1

Deep Domain Adversarial Adaptation for Photon-efficient Imaging

2 code implementations7 Jan 2022 YiWei Chen, Gongxin Yao, Yong liu, Hongye Su, Xiaomin Hu, Yu Pan

Photon-efficient imaging with the single-photon light detection and ranging (LiDAR) captures the three-dimensional (3D) structure of a scene by only a few detected signal photons per pixel.

Domain Adaptation

Robust photon-efficient imaging using a pixel-wise residual shrinkage network

2 code implementations5 Jan 2022 Gongxin Yao, YiWei Chen, Yong liu, Xiaomin Hu, Yu Pan

Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios.

Depth Estimation

Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase

no code implementations CVPR 2022 Huayi Tang, Yong liu

However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views.

Dynamically Stable Poincaré Embeddings for Neural Manifolds

no code implementations21 Dec 2021 Jun Chen, Yuang Liu, Xiangrui Zhao, Mengmeng Wang, Yong liu

As a result, we prove that, if initial metrics have an $L^2$-norm perturbation which deviates from the Hyperbolic metric on the Poincar\'e ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric.

Image Classification

SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Network

no code implementations20 Dec 2021 Xianfang Zeng, Jiangning Zhang, Liang Liu, Guangzhong Tian, Yong liu

To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild.


Searching Parameterized AP Loss for Object Detection

1 code implementation NeurIPS 2021 Chenxin Tao, Zizhang Li, Xizhou Zhu, Gao Huang, Yong liu, Jifeng Dai

In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.

object-detection Object Detection

MSP : Refine Boundary Segmentation via Multiscale Superpixel

no code implementations3 Dec 2021 Jie Zhu, Huabin Huang, Banghuai Li, Yong liu, Leye Wang

Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.

Scene Parsing Semantic Segmentation

Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation

no code implementations NeurIPS 2021 Shaogao Lv, Junhui Wang, Jiankun Liu, Yong liu

In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation.

Towards Sharper Generalization Bounds for Structured Prediction

no code implementations NeurIPS 2021 Shaojie Li, Yong liu

In the smoothness scenario, we provide generalization bounds that are not only a logarithmic dependency on the label set cardinality but a faster convergence rate of order $\mathcal{O}(\frac{1}{n})$ on the sample size $n$.

Generalization Bounds Structured Prediction

Refined Learning Bounds for Kernel and Approximate $k$-Means

no code implementations NeurIPS 2021 Yong liu

In this paper, we study the statistical properties of kernel $k$-means and Nystr\"{o}m-based kernel $k$-means, and obtain optimal clustering risk bounds, which improve the existing risk bounds.

Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN

no code implementations25 Nov 2021 Wen Yu, Baiying Lei, Yanyan Shen, Shuqiang Wang, Yong liu, Zhiguang Feng, Yong Hu, Michael K. Ng

In this work, a novel Multidirectional Perception Generative Adversarial Network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages.

MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation

no code implementations21 Nov 2021 Zizhang Li, Mengmeng Wang, Jianbiao Mei, Yong liu

Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions.

Image Segmentation Referring Expression Segmentation +1

Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application

no code implementations17 Nov 2021 Yulan Hu, Yong liu

Benefiting from the strong ability of the pre-trained model, the research on Chinese Word Segmentation (CWS) has made great progress in recent years.

Chinese Word Segmentation Language Modelling

Thoughts on the Consistency between Ricci Flow and Neural Network Behavior

no code implementations16 Nov 2021 Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu

During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.

A layer-stress learning framework universally augments deep neural network tasks

no code implementations14 Nov 2021 Shihao Shao, Yong liu, Qinghua Cui

Here we presented a layer-stress deep learning framework (x-NN) which implemented automatic and wise depth decision on shallow or deep feature map in a deep network through firstly designing enough number of layers and then trading off them by Multi-Head Attention Block.

Learning Rates for Nonconvex Pairwise Learning

no code implementations9 Nov 2021 Shaojie Li, Yong liu

We first successfully establish learning rates for these algorithms in a general nonconvex setting, where the analysis sheds insights on the trade-off between optimization and generalization and the role of early-stopping.

Metric Learning

Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking

no code implementations28 Oct 2021 Mengmeng Wang, Xiaoqian Yang, Yong liu

Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions.

Contrastive Learning Visual Object Tracking +1

Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation

no code implementations20 Oct 2021 Yidan Hu, Yong liu, Chunyan Miao, Gongqi Lin, Yuan Miao

In this paper, we propose a novel explanation generation framework, named Hierarchical Aspect-guided explanation Generation (HAG), for explainable recommendation.

Explainable Recommendation Explanation Generation +1

Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs

1 code implementation20 Oct 2021 Kaichao You, Yong liu, Ziyang Zhang, Jianmin Wang, Michael I. Jordan, Mingsheng Long

(2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top $K$ ranked PTMs via a Bayesian procedure that we propose.

A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Disease

no code implementations12 Oct 2021 Qiankun Zuo, Baiying Lei, Shuqiang Wang, Yong liu, BingChuan Wang, Yanyan Shen

The proposed model can evaluate characteristics of abnormal brain connections at different stages of Alzheimer's disease, which is helpful for cognitive disease study and early treatment.

Representation Learning

DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease

no code implementations12 Oct 2021 Junren Pan, Baiying Lei, Shuqiang Wang, BingChuan Wang, Yong liu, Yanyan Shen

In this work, a novel decoupling generative adversarial network (DecGAN) is proposed to detect abnormal neural circuits for AD.

Inductive Representation Learning in Temporal Networks via Mining Neighborhood and Community Influences

1 code implementation1 Oct 2021 Meng Liu, Yong liu

Therefore, we propose a new inductive network representation learning method called MNCI by mining neighborhood and community influences in temporal networks.

Link Prediction Node Classification +1

Manifold Micro-Surgery with Linearly Nearly Euclidean Metrics

no code implementations29 Sep 2021 Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu

The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular.

Improved Generalization Risk Bounds for Meta-Learning with PAC-Bayes-kl Analysis

no code implementations29 Sep 2021 Jiechao Guan, Zhiwu Lu, Yong liu

In particular, we identify that when the number of training task is large, utilizing a prior generated from an informative hyperposterior can achieve the same order of PAC-Bayes-kl bound as that obtained through setting a localized distribution-dependent prior for a novel task.

Generalization Bounds Learning Theory +1

Geometry-Entangled Visual Semantic Transformer for Image Captioning

no code implementations29 Sep 2021 Ling Cheng, Wei Wei, Feida Zhu, Yong liu, Chunyan Miao

However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement.

Image Captioning

Sharpness-Aware Minimization in Large-Batch Training: Training Vision Transformer In Minutes

no code implementations29 Sep 2021 Yong liu, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, Yang You

Large-batch training is an important direction for distributed machine learning, which can improve the utilization of large-scale clusters and therefore accelerate the training process.

Mask and Understand: Evaluating the Importance of Parameters

no code implementations29 Sep 2021 Bowei Zhu, Yong liu

Influence functions are classic techniques from robust statistics based on first-order Taylor approximations that have been widely used in the machine learning community to estimate small perturbations of datasets accurately to the model.

Feature Importance

High Probability Generalization Bounds for Minimax Problems with Fast Rates

no code implementations ICLR 2022 Shaojie Li, Yong liu

In this paper, we provide improved generalization analyses for almost all existing generalization measures of minimax problems, which enables the minimax problems to establish sharper bounds of order $\mathcal{O}\left( 1/n \right)$, significantly, with high probability.

Distributed Computing Generalization Bounds

Riemannian Manifold Embeddings for Straight-Through Estimator

no code implementations29 Sep 2021 Jun Chen, Hanwen Chen, Jiangning Zhang, Yuang Liu, Tianxin Huang, Yong liu

Quantized Neural Networks (QNNs) aim at replacing full-precision weights $\boldsymbol{W}$ with quantized weights $\boldsymbol{\hat{W}}$, which make it possible to deploy large models to mobile and miniaturized devices easily.


Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

1 code implementation23 Sep 2021 Xuemeng Yang, Hao Zou, Xin Kong, Tianxin Huang, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang

Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information.

3D Semantic Scene Completion 3D Semantic Segmentation +2

A Survey on Reinforcement Learning for Recommender Systems

no code implementations22 Sep 2021 Yuanguo Lin, Yong liu, Fan Lin, Lixin Zou, Pengcheng Wu, Wenhua Zeng, Huanhuan Chen, Chunyan Miao

To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems.

Explainable Recommendation reinforcement-learning +2

ActionCLIP: A New Paradigm for Video Action Recognition

2 code implementations17 Sep 2021 Mengmeng Wang, Jiazheng Xing, Yong liu

Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune".

Action Classification Action Recognition In Videos +4

Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

2 code implementations ICCV 2021 Lina Liu, Xibin Song, Mengmeng Wang, Yong liu, Liangjun Zhang

Meanwhile, to guarantee that the day and night images contain the same information, the domain-separated network takes the day-time images and corresponding night-time images (generated by GAN) as input, and the private and invariant feature extractors are learned by orthogonality and similarity loss, where the domain gap can be alleviated, thus better depth maps can be expected.

Monocular Depth Estimation

Go Wider Instead of Deeper

1 code implementation25 Jul 2021 Fuzhao Xue, Ziji Shi, Futao Wei, Yuxuan Lou, Yong liu, Yang You

To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or model compressing along with the depth.

Image Classification

3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image

no code implementations23 Jul 2021 Bowen Hu, Baiying Lei, Shuqiang Wang, Yong liu, BingChuan Wang, Min Gan, Yanyan Shen

A branching predictor and several hierarchical attention pipelines are constructed to generate point clouds that accurately describe the incomplete images and then complete these point clouds with high quality.

3D Shape Reconstruction

A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction

no code implementations21 Jul 2021 Bowen Hu, Baiying Lei, Yanyan Shen, Yong liu, Shuqiang Wang

Fusing medical images and the corresponding 3D shape representation can provide complementary information and microstructure details to improve the operational performance and accuracy in brain surgery.

3D Shape Representation

Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction

no code implementations21 Jul 2021 Qiankun Zuo, Baiying Lei, Yanyan Shen, Yong liu, Zhiguang Feng, Shuqiang Wang

Then two hypergraphs are constructed from the latent representations and the adversarial network based on graph convolution is employed to narrow the distribution difference of hyperedge features.

alzheimer's disease detection Disease Prediction +1

Characterization Multimodal Connectivity of Brain Network by Hypergraph GAN for Alzheimer's Disease Analysis

no code implementations21 Jul 2021 Junren Pan, Baiying Lei, Yanyan Shen, Yong liu, Zhiguang Feng, Shuqiang Wang

Using multimodal neuroimaging data to characterize brain network is currently an advanced technique for Alzheimer's disease(AD) Analysis.

White Matter Fiber Tractography

Improved Learning Rates for Stochastic Optimization: Two Theoretical Viewpoints

no code implementations19 Jul 2021 Shaojie Li, Yong liu

the sample size $n$ for ERM and SGD with milder assumptions in convex learning and similar high probability rates of order $\mathcal{O} (1/n)$ in nonconvex learning, rather than in expectation.

Learning Theory Stochastic Optimization

Adaptive Course Recommendation System

no code implementations journal 2021 Yuanguo Lin, Shibo Feng, Fan Lin, Wenhua Zeng, Yong liu, Pengcheng Wu

In this paper, we propose a novel course recommendation framework, named Dynamic Attention and hierarchical Reinforcement Learning (DARL), to improve the adaptivity of the recommendation model.

Hierarchical Reinforcement Learning

Few-Shot Domain Adaptation with Polymorphic Transformers

1 code implementation10 Jul 2021 Shaohua Li, Xiuchao Sui, Jie Fu, Huazhu Fu, Xiangde Luo, Yangqin Feng, Xinxing Xu, Yong liu, Daniel Ting, Rick Siow Mong Goh

Thus, the chance of overfitting the annotations is greatly reduced, and the model can perform robustly on the target domain after being trained on a few annotated images.

Domain Adaptation

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

2 code implementations7 Jul 2021 Xin Zhou, Aixin Sun, Yong liu, Jie Zhang, Chunyan Miao

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.

Collaborative Filtering Self-Supervised Learning

SSC: Semantic Scan Context for Large-Scale Place Recognition

1 code implementation1 Jul 2021 Lin Li, Xin Kong, Xiangrui Zhao, Tianxin Huang, Yong liu

We also present a two-step global semantic ICP to obtain the 3D pose (x, y, yaw) used to align the point cloud to improve matching performance.

Translation Visual Place Recognition

SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure

no code implementations22 Jun 2021 Lin Li, Xin Kong, Xiangrui Zhao, Wanlong Li, Feng Wen, Hongbo Zhang, Yong liu

LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue.

3D Semantic Segmentation Loop Closure Detection

Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems

no code implementations9 Jun 2021 Yinan Zhang, Boyang Li, Yong liu, Hao Wang, Chunyan Miao

In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID).

Recommendation Systems

TransVOS: Video Object Segmentation with Transformers

1 code implementation1 Jun 2021 Jianbiao Mei, Mengmeng Wang, Yeneng Lin, Yi Yuan, Yong liu

Recently, Space-Time Memory Network (STM) based methods have achieved state-of-the-art performance in semi-supervised video object segmentation (VOS).

One-shot visual object segmentation Semantic Segmentation +1

Concurrent Adversarial Learning for Large-Batch Training

no code implementations ICLR 2022 Yong liu, Xiangning Chen, Minhao Cheng, Cho-Jui Hsieh, Yang You

Current methods usually use extensive data augmentation to increase the batch size, but we found the performance gain with data augmentation decreases as batch size increases, and data augmentation will become insufficient after certain point.

Data Augmentation

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

1 code implementation NeurIPS 2021 Jiangning Zhang, Chao Xu, Jian Li, Wenzhou Chen, Yabiao Wang, Ying Tai, Shuo Chen, Chengjie Wang, Feiyue Huang, Yong liu

Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.

Image Retrieval Retrieval

KECRS: Towards Knowledge-Enriched Conversational Recommendation System

no code implementations18 May 2021 Tong Zhang, Yong liu, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions.

Entity Embeddings Knowledge Graphs +3

CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation

1 code implementation Findings (ACL) 2021 Chujie Zheng, Yong liu, Wei Chen, Yongcai Leng, Minlie Huang

However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.

Empathetic Response Generation Open-Domain Dialog +1

Towards Sharper Utility Bounds for Differentially Private Pairwise Learning

no code implementations7 May 2021 Yilin Kang, Yong liu, Jian Li, Weiping Wang

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.

DeepMI: Deep Multi-lead ECG Fusion for Identifying Myocardial Infarction and its Occurrence-time

no code implementations31 Mar 2021 Girmaw Abebe Tadesse, Hamza Javed, Yong liu, Jin Liu, Jiyan Chen, Komminist Weldemariam, Tingting Zhu

We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level.

Transfer Learning

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

1 code implementation22 Feb 2021 Kaichao You, Yong liu, Jianmin Wang, Mingsheng Long

In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models.

Model Selection regression +1

Large topological Hall effect near room temperature in noncollinear ferromagnet LaMn2Ge2 single crystal

no code implementations11 Feb 2021 Gaoshang Gong, Longmeng Xu, Yuming Bai, Yongqiang Wang, Songliu Yuan, Yong liu, Zhaoming Tian

Non-trivial spin structures in itinerant magnets can give rise to topological Hall effect (THE) due to the interacting local magnetic moments and conductive electrons.

Strongly Correlated Electrons

One-shot Face Reenactment Using Appearance Adaptive Normalization

no code implementations8 Feb 2021 Guangming Yao, Yi Yuan, Tianjia Shao, Shuang Li, Shanqi Liu, Yong liu, Mengmeng Wang, Kun Zhou

The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.

Face Reenactment

Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation

no code implementations5 Feb 2021 Jilin Tang, Yi Yuan, Tianjia Shao, Yong liu, Mengmeng Wang, Kun Zhou

In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.

Image Generation

Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning

no code implementations14 Jan 2021 Tongyu Zong, Chen Li, Yuanyuan Lei, Guangyu Li, Houwei Cao, Yong liu

In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning.

Ensemble Learning Time Series Analysis

Fast Estimation for Privacy and Utility in Differentially Private Machine Learning

no code implementations1 Jan 2021 Yuzhe Li, Yong liu, Weipinng Wang, Bo Li, Nan Liu

In this paper, we deduce the influence of $\epsilon$ on utility private learning models through strict mathematical derivation, and propose a novel approximate approach for estimating the utility of any $\epsilon$ value.

BIG-bench Machine Learning

Optimizing Quantized Neural Networks with Natural Gradient

no code implementations1 Jan 2021 Jun Chen, Hanwen Chen, Jiangning Zhang, Wenzhou Chen, Yong liu, Yunliang Jiang

Quantized Neural Networks (QNNs) have achieved an enormous step in improving computational efficiency, making it possible to deploy large models to mobile and miniaturized devices.

Effective Distributed Learning with Random Features: Improved Bounds and Algorithms

no code implementations ICLR 2021 Yong liu, Jiankun Liu, Shuqiang Wang

In this paper, we study the statistical properties of distributed kernel ridge regression together with random features (DKRR-RF), and obtain optimal generalization bounds under the basic setting, which can substantially relax the restriction on the number of local machines in the existing state-of-art bounds.

Generalization Bounds

RFNet: Recurrent Forward Network for Dense Point Cloud Completion

no code implementations ICCV 2021 Tianxin Huang, Hao Zou, Jinhao Cui, Xuemeng Yang, Mengmeng Wang, Xiangrui Zhao, Jiangning Zhang, Yi Yuan, Yifan Xu, Yong liu

The RFE extracts multiple global features from the incomplete point clouds for different recurrent levels, and the FDC generates point clouds in a coarse-to-fine pipeline.

Point Cloud Completion

A Hybrid Bandit Framework for Diversified Recommendation

no code implementations24 Dec 2020 Qinxu Ding, Yong liu, Chunyan Miao, Fei Cheng, Haihong Tang

Previous interactive recommendation methods primarily focus on learning users' personalized preferences on the relevance properties of an item set.

Recommendation Systems

CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth

no code implementations18 Dec 2020 Xingxing Zuo, Nathaniel Merrill, Wei Li, Yong liu, Marc Pollefeys, Guoquan Huang

In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings.

Depth Estimation Depth Prediction +1

Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation

no code implementations16 Dec 2020 Hao Tang, Xingwei Liu, Kun Han, Shanlin Sun, Narisu Bai, Xuming Chen, Huang Qian, Yong liu, Xiaohui Xie

State-of-the-art CNN segmentation models apply either 2D or 3D convolutions on input images, with pros and cons associated with each method: 2D convolution is fast, less memory-intensive but inadequate for extracting 3D contextual information from volumetric images, while the opposite is true for 3D convolution.

Image Segmentation Organ Segmentation +1

FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion

no code implementations15 Dec 2020 Lina Liu, Xibin Song, Xiaoyang Lyu, Junwei Diao, Mengmeng Wang, Yong liu, Liangjun Zhang

Then, a refined depth map is further obtained using a residual learning strategy in the coarse-to-fine stage with a coarse depth map and color image as input.

Depth Completion

Keyword-Guided Neural Conversational Model

1 code implementation15 Dec 2020 Peixiang Zhong, Yong liu, Hao Wang, Chunyan Miao

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast.

Knowledge Graphs Retrieval +1

HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation

1 code implementation14 Dec 2020 Xiaoyang Lyu, Liang Liu, Mengmeng Wang, Xin Kong, Lina Liu, Yong liu, Xinxin Chen, Yi Yuan

To obtainmore accurate depth estimation in large gradient regions, itis necessary to obtain high-resolution features with spatialand semantic information.

Monocular Depth Estimation Self-Supervised Learning

FlowMOT: 3D Multi-Object Tracking by Scene Flow Association

no code implementations14 Dec 2020 Guangyao Zhai, Xin Kong, Jinhao Cui, Yong liu, Zhen Yang

Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability.

3D Multi-Object Tracking Association +2

DLPAlign: A Deep Learning based Progressive Alignment Method for Multiple Protein Sequences

1 code implementation21 Nov 2020 Mengmeng Kuang, Yong liu, Lufei Gao

This paper proposed a novel and straightforward approach to improve the accuracy of progressive multiple protein sequence alignment method.

Decision Making Multiple Sequence Alignment +1

Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain

no code implementations9 Nov 2020 Senrong You, Yong liu, Baiying Lei, Shuqiang Wang

Specifically, FP-GANs firstly divides an MR image into low-frequency global approximation and high-frequency anatomical texture in wavelet domain.

Image Super-Resolution

HILONet: Hierarchical Imitation Learning from Non-Aligned Observations

no code implementations5 Nov 2020 Shanqi Liu, Junjie Cao, Wenzhou Chen, Licheng Wen, Yong liu

In this work, we propose a new imitation learning approach called Hierarchical Imitation Learning from Observation(HILONet), which adopts a hierarchical structure to choose feasible sub-goals from demonstrated observations dynamically.

Imitation Learning

CL-MAPF: Multi-Agent Path Finding for Car-Like Robots with Kinematic and Spatiotemporal Constraints

1 code implementation1 Nov 2020 Licheng Wen, Zhen Zhang, Zhe Chen, Xiangrui Zhao, Yong liu

In this paper, we give a mathematical formalization of Multi-Agent Path Finding for Car-Like robots (CL-MAPF) problem.

Robotics Multiagent Systems

APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment

1 code implementation25 Oct 2020 Jiangning Zhang, Xianfang Zeng, Chao Xu, Jun Chen, Yong liu, Yunliang Jiang

Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio.

Face Reenactment

Semantic Graph Based Place Recognition for 3D Point Clouds

1 code implementation26 Aug 2020 Xin Kong, Xuemeng Yang, Guangyao Zhai, Xiangrui Zhao, Xianfang Zeng, Mengmeng Wang, Yong liu, Wanlong Li, Feng Wen

First, we propose a novel semantic graph representation for the point cloud scenes by reserving the semantic and topological information of the raw point cloud.

Graph Matching Graph Similarity

LIC-Fusion 2.0: LiDAR-Inertial-Camera Odometry with Sliding-Window Plane-Feature Tracking

no code implementations17 Aug 2020 Xingxing Zuo, Yulin Yang, Patrick Geneva, Jiajun Lv, Yong liu, Guoquan Huang, Marc Pollefeys

Only the tracked planar points belonging to the same plane will be used for plane initialization, which makes the plane extraction efficient and robust.


Targetless Calibration of LiDAR-IMU System Based on Continuous-time Batch Estimation

2 code implementations29 Jul 2020 Jiajun Lv, Jinhong Xu, Kewei Hu, Yong liu, Xingxing Zuo

Sensor calibration is the fundamental block for a multi-sensor fusion system.


Dive Deeper Into Box for Object Detection

no code implementations ECCV 2020 Ran Chen, Yong liu, Mengdan Zhang, Shu Liu, Bei Yu, Yu-Wing Tai

Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods.

object-detection Object Detection

Neural Architecture Optimization with Graph VAE

no code implementations18 Jun 2020 Jian Li, Yong liu, Jiankun Liu, Weiping Wang

The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.

Neural Architecture Search

Collision-free Trajectory Planning for Autonomous Surface Vehicle

no code implementations20 May 2020 Licheng Wen, Jiaqing Yan, Xuemeng Yang, Yong liu, Yong Gu

We apply a numerical optimization method in the back-end to generate the trajectory.


Hierarchical and Efficient Learning for Person Re-Identification

no code implementations18 May 2020 Jiangning Zhang, Liang Liu, Chao Xu, Yong liu

Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e. g. model size and latency, which are critical for practical application.

Person Re-Identification

APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals

3 code implementations30 Apr 2020 Jiangning Zhang, Liang Liu, Zhu-Cun Xue, Yong liu

Audio-guided face reenactment aims at generating photorealistic faces using audio information while maintaining the same facial movement as when speaking to a real person.

Face Reenactment

Towards Persona-Based Empathetic Conversational Models

1 code implementation EMNLP 2020 Peixiang Zhong, Chen Zhang, Hao Wang, Yong liu, Chunyan Miao

To this end, we propose a new task towards persona-based empathetic conversations and present the first empirical study on the impact of persona on empathetic responding.

Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph

no code implementations24 Apr 2020 Susen Yang, Yong liu, Yonghui Xu, Chunyan Miao, Min Wu, Juyong Zhang

Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation.

Graph Attention

Learning Hierarchical Review Graph Representations for Recommendation

no code implementations24 Apr 2020 Yong liu, Susen Yang, Yinan Zhang, Chunyan Miao, Zaiqing Nie, Juyong Zhang

Therefore, they may not be effective in capturing the global dependency between words, and tend to be easily biased by noise review information.

Graph Attention

Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations

1 code implementation12 Apr 2020 Shaohua Li, Xiuchao Sui, Jie Fu, Yong liu, Rick Siow Mong Goh

To make CNNs more invariant to transformations, we propose "Feature Lenses", a set of ad-hoc modules that can be easily plugged into a trained model (referred to as the "host model").

A Learning Framework for n-bit Quantized Neural Networks toward FPGAs

1 code implementation6 Apr 2020 Jun Chen, Liang Liu, Yong liu, Xianfang Zeng

Furthermore, we also design a shift vector processing element (SVPE) array to replace all 16-bit multiplications with SHIFT operations in convolution operation on FPGAs.

Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose

no code implementations29 Mar 2020 Xianfang Zeng, Yusu Pan, Mengmeng Wang, Jiangning Zhang, Yong liu

On the one hand, we adopt the deforming autoencoder to disentangle identity and pose representations.

Face Reenactment

Extended Feature Pyramid Network for Small Object Detection

1 code implementation16 Mar 2020 Chunfang Deng, Mengmeng Wang, Liang Liu, Yong liu

Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels.

object-detection Small Object Detection

Nearly Optimal Clustering Risk Bounds for Kernel K-Means

no code implementations9 Mar 2020 Yong Liu, Lizhong Ding, Weiping Wang

In this paper, we study the statistical properties of kernel $k$-means and obtain a nearly optimal excess clustering risk bound, substantially improving the state-of-art bounds in the existing clustering risk analyses.

Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss and RKHS

no code implementations9 Mar 2020 Yong Liu, Lizhong Ding, Weiping Wang

However, the studies on learning theory for general loss functions and hypothesis spaces remain limited.

Learning Theory

Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks

no code implementations4 Mar 2020 Jun Chen, Yong liu, Hao Zhang, Shengnan Hou, Jian Yang

Meanwhile, we propose a M-bit Inputs and N-bit Weights Network (MINW-Net) trained by AQE, a quantized neural network with 1-3 bits weights and activations.