Search Results for author: Bo Zhang

Found 256 papers, 126 papers with code

Understanding and Stabilizing GANs' Training Dynamics Using Control Theory

no code implementations ICML 2020 Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang

There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.

DeepSeek-VL: Towards Real-World Vision-Language Understanding

2 code implementations8 Mar 2024 Haoyu Lu, Wen Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, Yaofeng Sun, Chengqi Deng, Hanwei Xu, Zhenda Xie, Chong Ruan

The DeepSeek-VL family (both 1. 3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks.

Chatbot Language Modelling +3

VisionLLaMA: A Unified LLaMA Interface for Vision Tasks

1 code implementation1 Mar 2024 Xiangxiang Chu, Jianlin Su, Bo Zhang, Chunhua Shen

Large language models are built on top of a transformer-based architecture to process textual inputs.

Image Classification Image Generation +2

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

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

1 code implementation22 Feb 2024 Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li

Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.

OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving

1 code implementation6 Feb 2024 Guohang Yan, Jiahao Pi, Jianfei Guo, Zhaotong Luo, Min Dou, Nianchen Deng, Qiusheng Huang, Daocheng Fu, Licheng Wen, Pinlong Cai, Xing Gao, Xinyu Cai, Bo Zhang, Xuemeng Yang, Yeqi Bai, Hongbin Zhou, Botian Shi

With the development of implicit rendering technology and in-depth research on using generative models to produce data at scale, we propose OASim, an open and adaptive simulator and autonomous driving data generator based on implicit neural rendering.

Autonomous Driving Neural Rendering +1

Cross-Task Linearity Emerges in the Pretraining-Finetuning Paradigm

no code implementations6 Feb 2024 Zhanpeng Zhou, Zijun Chen, Yilan Chen, Bo Zhang, Junchi Yan

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning.

MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

1 code implementation6 Feb 2024 Xiangxiang Chu, Limeng Qiao, Xinyu Zhang, Shuang Xu, Fei Wei, Yang Yang, Xiaofei Sun, Yiming Hu, Xinyang Lin, Bo Zhang, Chunhua Shen

We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance.

AutoML Language Modelling

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

1 code implementation29 Jan 2024 Sifan Zhou, Liang Li, Xinyu Zhang, Bo Zhang, Shipeng Bai, Miao Sun, Ziyu Zhao, Xiaobo Lu, Xiangxiang Chu

To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup.

3D Object Detection Autonomous Vehicles +3

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

An Event-Oriented Diffusion-Refinement Method for Sparse Events Completion

no code implementations6 Jan 2024 Bo Zhang, Yuqi Han, Jinli Suo, Qionghai Dai

Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames, and feature ultra-high sensitivity at low bandwidth.

Rethinking of Feature Interaction for Multi-task Learning on Dense Prediction

no code implementations21 Dec 2023 Jingdong Zhang, Jiayuan Fan, Peng Ye, Bo Zhang, Hancheng Ye, Baopu Li, Yancheng Cai, Tao Chen

In this work, we propose to learn a comprehensive intermediate feature globally from both task-generic and task-specific features, we reveal an important fact that this intermediate feature, namely the bridge feature, is a good solution to the above issues.

Multi-Task Learning

Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation

no code implementations12 Dec 2023 Yuanbin Wang, Shaofei Huang, Yulu Gao, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Si Liu

In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels.

3D Semantic Segmentation Point Cloud Segmentation +2

Lenna: Language Enhanced Reasoning Detection Assistant

1 code implementation5 Dec 2023 Fei Wei, Xinyu Zhang, Ailing Zhang, Bo Zhang, Xiangxiang Chu

To evaluate the reasoning capability of Lenna, we construct a ReasonDet dataset to measure its performance on reasoning-based detection.

World Knowledge

Masked Autoencoders Are Robust Neural Architecture Search Learners

no code implementations20 Nov 2023 Yiming Hu, Xiangxiang Chu, Bo Zhang

Neural Architecture Search (NAS) currently relies heavily on labeled data, which is both expensive and time-consuming to acquire.

Image Reconstruction Neural Architecture Search

MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization

1 code implementation6 Nov 2023 Dongcheng Zou, Senzhang Wang, Xuefeng Li, Hao Peng, Yuandong Wang, Chunyang Liu, Kehua Sheng, Bo Zhang

Based on this, we propose a relative structural entropy-based position encoding and a multi-head attention masking scheme based on multi-layer encoding trees.

Management Position +2

A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations

1 code implementation31 Oct 2023 Hui Ma, Jian Wang, Hongfei Lin, Bo Zhang, Yijia Zhang, Bo Xu

Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines.

Multimodal Emotion Recognition

Virtual Accessory Try-On via Keypoint Hallucination

no code implementations26 Oct 2023 Junhong Gou, Bo Zhang, Li Niu, Jianfu Zhang, Jianlou Si, Chen Qian, Liqing Zhang

Specifically, our approach learns the human body priors and hallucinates the target locations of specified foreground keypoints in the background.

Hallucination Semantic Segmentation +1

Multiple Key-value Strategy in Recommendation Systems Incorporating Large Language Model

no code implementations25 Oct 2023 Dui Wang, Xiangyu Hou, XiaoHui Yang, Bo Zhang, Renbing Chen, Daiyue Xue

Recommendation system (RS) plays significant roles in matching users information needs for Internet applications, and it usually utilizes the vanilla neural network as the backbone to handle embedding details.

Language Modelling Large Language Model +1

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

1 code implementation25 Oct 2023 Jingxiang Sun, Bo Zhang, Ruizhi Shao, Lizhen Wang, Wen Liu, Zhenda Xie, Yebin Liu

The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene.

Improving Seq2Seq Grammatical Error Correction via Decoding Interventions

1 code implementation23 Oct 2023 Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token.

Grammatical Error Correction Language Modelling

DreamCom: Finetuning Text-guided Inpainting Model for Image Composition

no code implementations27 Sep 2023 Lingxiao Lu, Jiangtong Li, Bo Zhang, Li Niu

The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image.

Image Inpainting Object +1

StructChart: Perception, Structuring, Reasoning for Visual Chart Understanding

1 code implementation20 Sep 2023 Renqiu Xia, Bo Zhang, Haoyang Peng, Hancheng Ye, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan

Charts are common in literature across different scientific fields, conveying rich information easily accessible to readers.

Ranked #17 on Chart Question Answering on ChartQA (using extra training data)

Chart Question Answering Language Modelling +2

Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection

1 code implementation19 Sep 2023 Shaocong Xu, Pengfei Li, Xinyu Liu, Qianpu Sun, Yang Li, Shihui Guo, Zhen Wang, Bo Jiang, Rui Wang, Kehua Sheng, Bo Zhang, Hao Zhao

We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.

Anomaly Detection Autonomous Driving +1

SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving

1 code implementation19 Sep 2023 Xiangchao Yan, Runjian Chen, Bo Zhang, Jiakang Yuan, Xinyu Cai, Botian Shi, Wenqi Shao, Junchi Yan, Ping Luo, Yu Qiao

Our contributions are threefold: (1) Occupancy prediction is shown to be promising for learning general representations, which is demonstrated by extensive experiments on plenty of datasets and tasks.

3D Object Detection Autonomous Driving +3

Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors

1 code implementation15 Sep 2023 Yancheng Cai, Bo Zhang, Baopu Li, Tao Chen, Hongliang Yan, Jingdong Zhang, Jiahao Xu

Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage.

Pedestrian Detection

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

2 code implementations11 Sep 2023 Bo Zhang, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao

Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs.

Autonomous Driving Domain Generalization

Norm Tweaking: High-performance Low-bit Quantization of Large Language Models

no code implementations6 Sep 2023 Liang Li, Qingyuan Li, Bo Zhang, Xiangxiang Chu

On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones.

Model Compression Quantization

FPTQ: Fine-grained Post-Training Quantization for Large Language Models

no code implementations30 Aug 2023 Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao, Bo Zhang, Xiangxiang Chu, Yerui Sun, Li Du, Yuchen Xie

In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.

Quantization

ControlCom: Controllable Image Composition using Diffusion Model

1 code implementation19 Aug 2023 Bo Zhang, Yuxuan Duan, Jun Lan, Yan Hong, Huijia Zhu, Weiqiang Wang, Li Niu

To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition.

Image Harmonization

Foreground Object Search by Distilling Composite Image Feature

1 code implementation ICCV 2023 Bo Zhang, Jiacheng Sui, Li Niu

Additionally, previous works did not release their datasets, so we contribute two datasets for FOS task: S-FOSD dataset with synthetic composite images and R-FOSD dataset with real composite images.

Object Retrieval

ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation

1 code implementation1 Aug 2023 Bo Zhang, Jian Wang, Hui Ma, Bo Xu, Hongfei Lin

To overcome this challenge, we propose an innovative multimodal framework, called ZRIGF, which assimilates image-grounded information for dialogue generation in zero-resource situations.

Dialogue Generation Response Generation

Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling

1 code implementation CVPR 2023 Zhanhao Hu, Wenda Chu, Xiaopei Zhu, HUI ZHANG, Bo Zhang, Xiaolin Hu

In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures.

A Collaborative Transfer Learning Framework for Cross-domain Recommendation

no code implementations26 Jun 2023 Wei zhang, Pengye Zhang, Bo Zhang, Xingxing Wang, Dong Wang

The disadvantage of the former is that the data from other domains is not utilized by a single domain model, while the latter leverage all the data from different domains, but the fine-tuned model of transfer learning may trap the model in a local optimum of the source domain, making it difficult to fit the target domain.

Click-Through Rate Prediction Recommendation Systems +1

Estimating the Causal Effect of Early ArXiving on Paper Acceptance

2 code implementations24 Jun 2023 Yanai Elazar, Jiayao Zhang, David Wadden, Bo Zhang, Noah A. Smith

However, since quality is a challenging construct to estimate, we use the negative outcome control method, using paper citation count as a control variable to debias the quality confounding effect.

Causal Inference

Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction

no code implementations5 Jun 2023 Huinan Sun, Guangliang Yu, Pengye Zhang, Bo Zhang, Xingxing Wang, Dong Wang

It consists of a multi-interest graph structure for capturing long-term user behavior, a multi-scenario heterogeneous sequence model for modeling short-term information, then an adaptive fusion mechanism to fused information from long-term and short-term behaviors.

Click-Through Rate Prediction

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

1 code implementation NeurIPS 2023 Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks.

Autonomous Driving Point Cloud Pre-training

Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness

1 code implementation28 May 2023 Zhanhao Hu, Jun Zhu, Bo Zhang, Xiaolin Hu

Recent works found that deep neural networks (DNNs) can be fooled by adversarial examples, which are crafted by adding adversarial noise on clean inputs.

NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts

1 code implementation25 May 2023 Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li, Chen Li, Fei Huang, Min Zhang

We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains.

Grammatical Error Correction

SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification

2 code implementations16 May 2023 Siyuan Huang, Bo Zhang, Botian Shi, Peng Gao, Yikang Li, Hongsheng Li

In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model.

3D Point Cloud Classification Domain Generalization +2

Network pharmacology on the mechanism of Yi Qi Tong Qiao Pill inhibiting allergic rhinitis

no code implementations6 May 2023 Boyang Wang, DingFan Zhang, Tingyu Zhang, Chayanis Sutcharitchan, Jianlin Hua, Dongfang Hua, Bo Zhang, Shao Li

Network target analysis was performed to explore the potential mechanisms of YQTQP in the treatment of AR and the mechanisms were classified into different modules according to their biological functions.

Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?

no code implementations20 Apr 2023 Haoyang Peng, Baopu Li, Bo Zhang, Xin Chen, Tao Chen, Hongyuan Zhu

Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models.

Autonomous Driving Classification +3

Delving into Shape-aware Zero-shot Semantic Segmentation

1 code implementation CVPR 2023 Xinyu Liu, Beiwen Tian, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Hao Zhao, Guyue Zhou

Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.

Image Segmentation Segmentation +2

A Closer Look at Few-Shot 3D Point Cloud Classification

1 code implementation31 Mar 2023 Chuangguan Ye, Hongyuan Zhu, Bo Zhang, Tao Chen

In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes.

Few-Shot 3D Point Cloud Classification Few-Shot Learning +1

Pi-ViMo: Physiology-inspired Robust Vital Sign Monitoring using mmWave Radars

no code implementations24 Mar 2023 Bo Zhang, Boyu Jiang, Rong Zheng, XiaoPing Zhang, Jun Li, Qiang Xu

In this paper, we address these limitations and present "Pi-ViMo", a non-contact Physiology-inspired Robust Vital Sign Monitoring system, using mmWave radars.

Template Matching

MMFormer: Multimodal Transformer Using Multiscale Self-Attention for Remote Sensing Image Classification

no code implementations23 Mar 2023 Bo Zhang, Zuheng Ming, Wei Feng, Yaqian Liu, Liang He, Kaixing Zhao

To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data such as Light Detection and Ranging (LiDAR).

Image Classification Remote Sensing Image Classification

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

1 code implementation21 Mar 2023 Hancheng Ye, Bo Zhang, Tao Chen, Jiayuan Fan, Bin Wang

Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance.

Model Compression

Language-Driven Anchors for Zero-Shot Adversarial Robustness

1 code implementation30 Jan 2023 Xiao Li, Wei zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu

Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial robustness an open question.

Adversarial Defense Adversarial Robustness +3

AI of Brain and Cognitive Sciences: From the Perspective of First Principles

no code implementations20 Jan 2023 Luyao Chen, Zhiqiang Chen, Longsheng Jiang, Xiang Liu, Linlu Xu, Bo Zhang, Xiaolong Zou, Jinying Gao, Yu Zhu, Xizi Gong, Shan Yu, Sen Song, Liangyi Chen, Fang Fang, Si Wu, Jia Liu

Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation.

Few-Shot Learning Image Classification

Danlu Tongdu tablets treat lumbar spinal stenosis through reducing reactive oxygen species and apoptosis by regulating CDK2/CDK4/CDKN1A expression

no code implementations18 Jan 2023 Xue Bai, Ayesha T. Tahir, Zhengheng Yu, Wenbo Cheng, Bo Zhang, Jun Kang

Furthermore, the flow cytometry results showed that DLTD tablets efficiently reduced ROS content and inhibited rat neural stem cell apoptosis induced by hydrogen peroxide.

DarkVision: A Benchmark for Low-light Image/Video Perception

no code implementations16 Jan 2023 Bo Zhang, Yuchen Guo, Runzhao Yang, Zhihong Zhang, Jiayi Xie, Jinli Suo, Qionghai Dai

In this paper, we contribute the first multi-illuminance, multi-camera, and low-light dataset, named DarkVision, serving for both image enhancement and object detection.

Autonomous Driving Image Enhancement +5

YOLOv6 v3.0: A Full-Scale Reloading

5 code implementations13 Jan 2023 Chuyi Li, Lulu Li, Yifei Geng, Hongliang Jiang, Meng Cheng, Bo Zhang, Zaidan Ke, Xiaoming Xu, Xiangxiang Chu

For a glimpse of performance, our YOLOv6-N hits 37. 5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU.

Real-Time Object Detection

Fine-grained Visible Watermark Removal

no code implementations ICCV 2023 Li Niu, Xing Zhao, Bo Zhang, Liqing Zhang

Visible watermark removal aims to erase the watermark from watermarked image and recover the background image, which is a challenging task due to the diverse watermarks.

Image Cropping With Spatial-Aware Feature and Rank Consistency

no code implementations CVPR 2023 Chao Wang, Li Niu, Bo Zhang, Liqing Zhang

To address the first issue, we propose spatial-aware feature to encode the spatial relationship between candidate crops and aesthetic elements, by feeding the concatenation of crop mask and selectively aggregated feature maps to a light-weighted encoder.

Image Cropping

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

1 code implementation26 Dec 2022 Xingxing Wei, Ying Guo, Jie Yu, Bo Zhang

Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency.

Face Recognition Position +2

UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline

1 code implementation20 Dec 2022 Ben Fei, Siyuan Huang, Jiakang Yuan, Botian Shi, Bo Zhang, Weidong Yang, Min Dou, Yikang Li

Different from previous studies that only focus on a single adaptation task, UniDA3D can tackle several adaptation tasks in 3D segmentation field, by designing a unified source-and-target active sampling strategy, which selects a maximally-informative subset from both source and target domains for effective model adaptation.

3D Semantic Segmentation Domain Generalization +2

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion

no code implementations CVPR 2023 Tengfei Wang, Bo Zhang, Ting Zhang, Shuyang Gu, Jianmin Bao, Tadas Baltrusaitis, Jingjing Shen, Dong Chen, Fang Wen, Qifeng Chen, Baining Guo

This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields.

Computational Efficiency

Make RepVGG Greater Again: A Quantization-aware Approach

2 code implementations3 Dec 2022 Xiangxiang Chu, Liang Li, Bo Zhang

Nonetheless, its quantization performance is usually too poor to deploy (more than 20% top-1 accuracy drop on ImageNet) when INT8 inference is desired.

Quantization Semantic Segmentation

Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation

no code implementations15 Nov 2022 Weimin Wu, Jiayuan Fan, Tao Chen, Hancheng Ye, Bo Zhang, Baopu Li

To enhance the model, adaptability between domains and reduce the computational cost when deploying the ensemble model, we propose a novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model.

Knowledge Distillation Unsupervised Domain Adaptation

Better Pre-Training by Reducing Representation Confusion

no code implementations9 Oct 2022 Haojie Zhang, Mingfei Liang, Ruobing Xie, Zhenlong Sun, Bo Zhang, Leyu Lin

Motivated by the above investigation, we propose two novel techniques to improve pre-trained language models: Decoupled Directional Relative Position (DDRP) encoding and MTH pre-training objective.

Language Modelling Position +1

EAPruning: Evolutionary Pruning for Vision Transformers and CNNs

no code implementations1 Oct 2022 Qingyuan Li, Bo Zhang, Xiangxiang Chu

In this paper, we undertake a simple and effective approach that can be easily applied to both vision transformers and convolutional neural networks.

3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation

1 code implementation12 Sep 2022 Junshu Tang, Bo Zhang, Binxin Yang, Ting Zhang, Dong Chen, Lizhuang Ma, Fang Wen

In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs.

3D Face Animation Disentanglement +3

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

Human-centric Image Cropping with Partition-aware and Content-preserving Features

1 code implementation21 Jul 2022 Bo Zhang, Li Niu, Xing Zhao, Liqing Zhang

Image cropping aims to find visually appealing crops in an image, which is an important yet challenging task.

Image Cropping

Aspect-specific Context Modeling for Aspect-based Sentiment Analysis

1 code implementation17 Jul 2022 Fang Ma, Chen Zhang, Bo Zhang, Dawei Song

Extensive experimental results on standard and adversarial benchmarks for SC and OE demonstrate the effectiveness and robustness of the proposed method, yielding new state-of-the-art performance on OE and competitive performance on SC.

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

Spatial Transformation for Image Composition via Correspondence Learning

no code implementations6 Jul 2022 Bo Zhang, Yue Liu, Kaixin Lu, Li Niu, Liqing Zhang

Instead, we propose a novel correspondence learning network (CorrelNet) to model the correspondence between foreground and background using cross-attention maps, based on which we can predict the target coordinate that each source coordinate of foreground should be mapped to on the background.

Virtual Try-on

Careful seeding for the k-medoids algorithm with incremental k++ cluster construction

no code implementations6 Jul 2022 Difei Cheng, Bo Zhang

An improved k-medoids algorithm (INCKM) was recently proposed to overcome this drawback, based on constructing a candidate medoids subset with a parameter choosing procedure, but it may fail when dealing with imbalanced datasets.

Clustering Computational Efficiency

Multi-granularity Item-based Contrastive Recommendation

no code implementations4 Jul 2022 Ruobing Xie, Zhijie Qiu, Bo Zhang, Leyu Lin

Specifically, we build three item-based CL tasks as a set of plug-and-play auxiliary objectives to capture item correlations in feature, semantic and session levels.

Contrastive Learning Recommendation Systems +1

Fast Lossless Neural Compression with Integer-Only Discrete Flows

1 code implementation17 Jun 2022 Siyu Wang, Jianfei Chen, Chongxuan Li, Jun Zhu, Bo Zhang

In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic.

Quantization

Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models

1 code implementation15 Jun 2022 Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu, Bo Zhang

Thus, the generation performance on a subset of timesteps is crucial, which is greatly influenced by the covariance design in DPMs.

Computational Efficiency

Asymptotic Inference for Infinitely Imbalanced Logistic Regression

no code implementations27 Apr 2022 Dorian Goldman, Bo Zhang

In this paper we extend the work of Owen (2007) by deriving a second order expansion for the slope parameter in logistic regression, when the size of the majority class is unbounded and the minority class is finite.

regression

Adaptable Text Matching via Meta-Weight Regulator

no code implementations27 Apr 2022 Bo Zhang, Chen Zhang, Fang Ma, Dawei Song

Neural text matching models have been used in a range of applications such as question answering and natural language inference, and have yielded a good performance.

Meta-Learning Natural Language Inference +2

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

1 code implementation25 Apr 2022 Hao Ouyang, Bo Zhang, Pan Zhang, Hao Yang, Jiaolong Yang, Dong Chen, Qifeng Chen, Fang Wen

We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.

Image-to-Image Translation Neural Rendering +1

MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction

2 code implementations NAACL 2022 Yue Zhang, Zhenghua Li, Zuyi Bao, Jiacheng Li, Bo Zhang, Chen Li, Fei Huang, Min Zhang

This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7, 063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources.

Grammatical Error Correction Sentence

Bringing Old Films Back to Life

1 code implementation CVPR 2022 Ziyu Wan, Bo Zhang, Dongdong Chen, Jing Liao

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films.

Analog Video Restoration

Exploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue

1 code implementation IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022 Bo Zhang, Jian Wang, Hongfei Lin, Hui Ma, Bo Xu

Correlation integration is designed to fully exploit the pairwise mutual information among dialogue context, knowledge, and responses, while overall integration adopts an integration gate to capture global information.

Dialogue Generation

Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation

1 code implementation3 Mar 2022 Bo Zhang, Tao Chen, Bin Wang

Although domain adaptation has been extensively studied in natural image-based segmentation task, the research on cross-domain segmentation for very high resolution (VHR) remote sensing images (RSIs) still remains underexplored.

Domain Adaptation Image Segmentation +2

Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Texts

no code implementations2 Feb 2022 Bo Zhang, Jiayao Zhang

We examine the role of textual data as study units when conducting causal inference by drawing parallels between human subjects and organized texts.

Causal Inference

Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models

2 code implementations ICLR 2022 Fan Bao, Chongxuan Li, Jun Zhu, Bo Zhang

In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w. r. t.

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

StyleSwin: Transformer-based GAN for High-resolution Image Generation

1 code implementation CVPR 2022 BoWen Zhang, Shuyang Gu, Bo Zhang, Jianmin Bao, Dong Chen, Fang Wen, Yong Wang, Baining Guo

To this end, we believe that local attention is crucial to strike the balance between computational efficiency and modeling capacity.

 Ranked #1 on Image Generation on CelebA 256x256 (FID metric)

Blocking Computational Efficiency +3

Contrastive Cross-domain Recommendation in Matching

1 code implementation2 Dec 2021 Ruobing Xie, Qi Liu, Liangdong Wang, Shukai Liu, Bo Zhang, Leyu Lin

Cross-domain recommendation (CDR) aims to provide better recommendation results in the target domain with the help of the source domain, which is widely used and explored in real-world systems.

Contrastive Learning Representation Learning +1

Vector Quantized Diffusion Model for Text-to-Image Synthesis

2 code implementations CVPR 2022 Shuyang Gu, Dong Chen, Jianmin Bao, Fang Wen, Bo Zhang, Dongdong Chen, Lu Yuan, Baining Guo

Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.

 Ranked #1 on Text-to-Image Generation on Oxford 102 Flowers (using extra training data)

Denoising Text-to-Image Generation

Entity Relation Extraction as Dependency Parsing in Visually Rich Documents

no code implementations EMNLP 2021 Yue Zhang, Bo Zhang, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao

Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i. e., semantic entity), while the relations in-between are largely unexplored.

Dependency Parsing Entity Linking +3

Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network

1 code implementation8 Oct 2021 Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Bo Zhang, Liefeng Bo

The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods.

Recommendation Systems Relation +1

Generating Transferable Adversarial Patch by Simultaneously Optimizing its Position and Perturbations

no code implementations29 Sep 2021 Xingxing Wei, Ying Guo, Jie Yu, Huanqian Yan, Bo Zhang

In this paper, we propose a method to simultaneously optimize the position and perturbation to generate transferable adversarial patches, and thus obtain high attack success rates in the black-box setting.

Face Recognition Position

Enhancing the Transferability of Adversarial Attacks via Scale Ensemble

no code implementations29 Sep 2021 Xianfeng Gao, Zhikai Chen, Bo Zhang

The experiments on ImageNet show that our method successfully mitigates the gap of transferability between models with different input sizes and achieves about 8% higher success rate comparing with the state-of-the-art input transformation methods.

Fast Density Estimation for Density-based Clustering Methods

no code implementations23 Sep 2021 Difei Cheng, Ruihang Xu, Bo Zhang, Ruinan Jin

Density-based clustering algorithms are widely used for discovering clusters in pattern recognition and machine learning since they can deal with non-hyperspherical clusters and are robustness to handle outliers.

Clustering Computational Efficiency +1

Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection

1 code implementation19 Sep 2021 Bo Zhang, Tao Chen, Bin Wang, Ruoyao Li

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.

Object object-detection +2

Densely Semantic Enhancement for Domain Adaptive Region-free Detectors

no code implementations30 Aug 2021 Bo Zhang, Tao Chen, Bin Wang, Xiaofeng Wu, Liming Zhang, Jiayuan Fan

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.

object-detection Object Detection +1

Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification

no code implementations30 Aug 2021 Yike Wu, Bo Zhang, Gang Yu, Weixi Zhang, Bin Wang, Tao Chen, Jiayuan Fan

The goal of few-shot fine-grained image classification is to recognize rarely seen fine-grained objects in the query set, given only a few samples of this class in the support set.

Fine-Grained Image Classification Object +3

OPA: Object Placement Assessment Dataset

3 code implementations5 Jul 2021 Liu Liu, Zhenchen Liu, Bo Zhang, Jiangtong Li, Li Niu, Qingyang Liu, Liqing Zhang

Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e. g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image.

Object

Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning

no code implementations30 Jun 2021 You Qiaoben, Chengyang Ying, Xinning Zhou, Hang Su, Jun Zhu, Bo Zhang

In this paper, we provide a framework to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space.

reinforcement-learning Reinforcement Learning (RL)

Making Images Real Again: A Comprehensive Survey on Deep Image Composition

3 code implementations28 Jun 2021 Li Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, Liqing Zhang

We have also contributed the first image composition toolbox: libcom https://github. com/bcmi/libcom, which assembles 10+ image composition related functions (e. g., image blending, image harmonization, object placement, shadow generation, generative composition).

Image Harmonization

Stability and Generalization of Bilevel Programming in Hyperparameter Optimization

1 code implementation NeurIPS 2021 Fan Bao, Guoqiang Wu, Chongxuan Li, Jun Zhu, Bo Zhang

Our results can explain some mysterious behaviours of the bilevel programming in practice, for instance, overfitting to the validation set.

Hyperparameter Optimization

A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents

1 code implementation NAACL 2021 Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang

Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.

Multi-Task Learning Opinion Mining +1

Robust Mutual Learning for Semi-supervised Semantic Segmentation

no code implementations1 Jun 2021 Pan Zhang, Bo Zhang, Ting Zhang, Dong Chen, Fang Wen

The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.

Pseudo Label Semi-Supervised Semantic Segmentation

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

8 code implementations NeurIPS 2021 Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.

Image Classification Semantic Segmentation

Microshift: An Efficient Image Compression Algorithm for Hardware

1 code implementation20 Apr 2021 Bo Zhang, Pedro V. Sander, Chi-Ying Tsui, Amine Bermak

In our method, the image is first micro-shifted, then the sub-quantized values are further compressed.

Data Compression Image Compression

Let's See Clearly: Contaminant Artifact Removal for Moving Cameras

no code implementations ICCV 2021 Xiaoyu Li, Bo Zhang, Jing Liao, Pedro V. Sander

This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.

Video Restoration

Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable

no code implementations15 Apr 2021 Shuxiao Chen, Bo Zhang

Estimating dynamic treatment regimes (DTRs) from retrospective observational data is challenging as some degree of unmeasured confounding is often expected.

Image Composition Assessment with Saliency-augmented Multi-pattern Pooling

1 code implementation7 Apr 2021 Bo Zhang, Li Niu, Liqing Zhang

Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image.

Aesthetics Quality Assessment

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

no code implementations CVPR 2021 Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Bo Zhang

This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks.

Extragalactic HI 21-cm absorption line observations with the Five-hundred-meter Aperture Spherical radio Telescope

no code implementations11 Mar 2021 Bo Zhang, Ming Zhu, Zhong-Zu Wu, Qing-Zheng Yu, Peng Jiang, You-Ling Yue, Meng-Lin Huang, Qiao-Li Hao

Our observations successfully confirmed the existence of HI absorption lines in all these systems, including two sources that were marginally detected by ALFALFA.

Astrophysics of Galaxies

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

1 code implementation CVPR 2021 Chulin Xie, Chuxin Wang, Bo Zhang, Hao Yang, Dong Chen, Fang Wen

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion.

 Ranked #1 on Point Cloud Completion on ShapeNet (Earth Mover's Distance metric)

Point Cloud Completion

A Minimax Probability Machine for Non-Decomposable Performance Measures

no code implementations28 Feb 2021 JunRu Luo, Hong Qiao, Bo Zhang

On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the accuracy rate, which makes it unsuitable to deal with imbalanced classification tasks.

Binary Classification Classification +2

Learning with Smooth Hinge Losses

no code implementations27 Feb 2021 JunRu Luo, Hong Qiao, Bo Zhang

Due to the non-smoothness of the Hinge loss in SVM, it is difficult to obtain a faster convergence rate with modern optimization algorithms.

text-classification Text Classification

Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network

no code implementations7 Feb 2021 Ruobing Xie, Qi Liu, Shukai Liu, Ziwei Zhang, Peng Cui, Bo Zhang, Leyu Lin

In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity.

Graph Attention Recommendation Systems

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

1 code implementation7 Feb 2021 Minfang Lu, Shuai Ning, Shuangrong Liu, Fengyang Sun, Bo Zhang, Bo Yang, Lin Wang

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details.

The Flare and Warp of the Young Stellar Disk traced with LAMOST DR5 OB-type stars

no code implementations1 Feb 2021 Yang Yu, Hai-Feng Wang, Wen-Yuan Cui, Lin-Lin Li, Chao Liu, Bo Zhang, Hao Tian, Zhen-Yan Huo, Jie Ju, Zhi-Cun Liu, Fang Wen, Shuai Feng

We present analysis of the spatial density structure for the outer disk from 8$-$14 \, kpc with the LAMOST DR5 13534 OB-type stars and observe similar flaring on north and south sides of the disk implying that the flaring structure is symmetrical about the Galactic plane, for which the scale height at different Galactocentric distance is from 0. 14 to 0. 5 \, kpc.

Astrophysics of Galaxies

Robust Dynamical Decoupling for the Manipulation of a Spin Network via a Single Spin

no code implementations11 Jan 2021 Xiaodong Yang, Yunrui Ge, Bo Zhang, Jun Li

High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.

Quantum Physics

Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2

no code implementations7 Jan 2021 Jing Li, Xiang-Xiang Xue, Chao Liu, Bo Zhang, Hans-Walter Rix, Jeffrey L. Carlin, Chengqun Yang, Rene A. Mendez, Jing Zhong, Hao Tian, Lan Zhang, Yan Xu, Yaqian Wu, Gang Zhao, Ruixiang Chang

Their location in [$\alpha$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$\alpha$/M] \textbf{lower} than the thick disk.

Astrophysics of Galaxies

HCGrid: A Convolution-based Gridding Framework for RadioAstronomy in Hybrid Computing Environments

1 code implementation24 Dec 2020 Hao Wang, Ce Yu, Bo Zhang, Jian Xiao, Qi Luo

Gridding operation, which is to map non-uniform data samples onto a uniformly distributedgrid, is one of the key steps in radio astronomical data reduction process.

Instrumentation and Methods for Astrophysics

A Unified Mixture-View Framework for Unsupervised Representation Learning

no code implementations26 Nov 2020 Xiangxiang Chu, Xiaohang Zhan, Bo Zhang

Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augmentation.

Data Augmentation object-detection +2

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation

no code implementations ICCV 2023 Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang, Bo Zhang, Xiaokang Yang, Junchi Yan

Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory.

Disentanglement Neural Architecture Search

Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models

1 code implementation NeurIPS Workshop ICBINB 2020 Fan Bao, Kun Xu, Chongxuan Li, Lanqing Hong, Jun Zhu, Bo Zhang

The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable.

Bi-level Score Matching for Learning Energy-based Latent Variable Models

1 code implementation NeurIPS 2020 Fan Bao, Chongxuan Li, Kun Xu, Hang Su, Jun Zhu, Bo Zhang

This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem.

Rolling Shutter Correction Stochastic Optimization

Old Photo Restoration via Deep Latent Space Translation

8 code implementations14 Sep 2020 Zi-Yu Wan, Bo Zhang, Dong-Dong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen

Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.

Image Restoration Translation

Deep Sketch-guided Cartoon Video Inbetweening

1 code implementation10 Aug 2020 Xiaoyu Li, Bo Zhang, Jing Liao, Pedro V. Sander

The key idea of the proposed approach is to estimate the dense cross-domain correspondence between the sketch and cartoon video frames, and employ a blending module with occlusion estimation to synthesize the middle frame guided by the sketch.

Image Generation Occlusion Estimation

Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

1 code implementation ECCV 2020 Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng, Hang Su, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang

Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.

Object Localization

Free-Space Optical Communication Using Non-mode-Selective Photonic Lantern Based Coherent Receiver

no code implementations3 Jul 2020 Bo Zhang, Renzhi Yuan, Jianfeng Sun, Julian Cheng, Mohamed-Slim Alouini

A free-space optical communication system using non-mode-selective photonic lantern (PL) based coherent receiver is studied.

Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks

no code implementations ACL 2020 Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang

The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.

Fine-Grained Opinion Analysis Multi-Task Learning

Noisy Differentiable Architecture Search

1 code implementation7 May 2020 Xiangxiang Chu, Bo Zhang

However, it largely suffers from the well-known performance collapse issue due to the aggregation of skip connections.

Image Classification Neural Architecture Search

Bringing Old Photos Back to Life

7 code implementations CVPR 2020 Zi-Yu Wan, Bo Zhang, Dong-Dong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen

Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.

Image Restoration Translation

Automatic, Dynamic, and Nearly Optimal Learning Rate Specification by Local Quadratic Approximation

1 code implementation7 Apr 2020 Yingqiu Zhu, Yu Chen, Danyang Huang, Bo Zhang, Hansheng Wang

In each update step, given the gradient direction, we locally approximate the loss function by a standard quadratic function of the learning rate.

Sex Differences in Severity and Mortality Among Patients With COVID-19: Evidence from Pooled Literature Analysis and Insights from Integrated Bioinformatic Analysis

no code implementations30 Mar 2020 Xiyi Wei, Yu-Tian Xiao, Jian Wang, Rui Chen, Wei zhang, Yue Yang, Daojun Lv, Chao Qin, Di Gu, Bo Zhang, Weidong Chen, Jianquan Hou, Ninghong Song, Guohua Zeng, Shancheng Ren

Objective: To conduct a meta-analysis of current studies that examined sex differences in severity and mortality in patients with COVID-19, and identify potential mechanisms underpinning these differences.

Perceptual Image Super-Resolution with Progressive Adversarial Network

no code implementations8 Mar 2020 Lone Wong, Deli Zhao, Shaohua Wan, Bo Zhang

Progressive growing enhances image resolution gradually, thereby preserving precision of recovered image.

Image Super-Resolution

User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization

no code implementations29 Feb 2020 Kang Wei, Jun Li, Ming Ding, Chuan Ma, Hang Su, Bo Zhang, H. Vincent Poor

According to our analysis, the UDP framework can realize $(\epsilon_{i}, \delta_{i})$-LDP for the $i$-th MT with adjustable privacy protection levels by varying the variances of the artificial noise processes.

Federated Learning Privacy Preserving

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

1 code implementation19 Feb 2020 Wen Wang, Wei zhang, Shukai Liu, Qi Liu, Bo Zhang, Leyu Lin, Hongyuan Zha

Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types.

Representation Learning

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

1 code implementation pproximateinference AABI Symposium 2019 Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu, Bo Zhang

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.

MixPath: A Unified Approach for One-shot Neural Architecture Search

1 code implementation ICCV 2023 Xiangxiang Chu, Shun Lu, Xudong Li, Bo Zhang

However, current two-stage neural architecture search methods are mainly limited to single-path search spaces.

Neural Architecture Search

Neural Architecture Search on Acoustic Scene Classification

no code implementations30 Dec 2019 Jixiang Li, Chuming Liang, Bo Zhang, Zhao Wang, Fei Xiang, Xiangxiang Chu

Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden.

Acoustic Scene Classification Classification +3

Latent Variables on Spheres for Autoencoders in High Dimensions

no code implementations21 Dec 2019 Deli Zhao, Jiapeng Zhu, Bo Zhang

Variational Auto-Encoder (VAE) has been widely applied as a fundamental generative model in machine learning.

Vocal Bursts Intensity Prediction

Triple Generative Adversarial Networks

1 code implementation20 Dec 2019 Chongxuan Li, Kun Xu, Jiashuo Liu, Jun Zhu, Bo Zhang

It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).

Classification Conditional Image Generation +4

Realization of spatial sparseness by deep ReLU nets with massive data

no code implementations16 Dec 2019 Charles K. Chui, Shao-Bo Lin, Bo Zhang, Ding-Xuan Zhou

The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality.

Learning Theory

Automatic quality assessment for 2D fetal sonographic standard plane based on multi-task learning

no code implementations11 Dec 2019 Hong Luo, Han Liu, Kejun Li, Bo Zhang

An essential criterion for FS image quality control is that all the essential anatomical structures in the section should appear full and remarkable with a clear boundary.

Image Quality Assessment Multi-Task Learning +1

Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure

1 code implementation22 Nov 2019 Zhijie Deng, Yucen Luo, Jun Zhu, Bo Zhang

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights.

Bayesian Inference Neural Architecture Search +2

Hierarchy Response Learning for Neural Conversation Generation

no code implementations IJCNLP 2019 Bo Zhang, Xiao-Ming Zhang

Specifically, a hierarchical response generation (HRG) framework is proposed to capture the conversation intention in a natural and coherent way.

Response Generation

Understanding and Stabilizing GANs' Training Dynamics with Control Theory

1 code implementation29 Sep 2019 Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang

There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.

Ranked #37 on Image Generation on CIFAR-10 (Inception score metric)

Image Generation L2 Regularization

Pruning from Scratch

1 code implementation27 Sep 2019 Yulong Wang, Xiaolu Zhang, Lingxi Xie, Jun Zhou, Hang Su, Bo Zhang, Xiaolin Hu

Network pruning is an important research field aiming at reducing computational costs of neural networks.

Network Pruning

Deep Bayesian Structure Networks

1 code implementation25 Sep 2019 Zhijie Deng, Yucen Luo, Jun Zhu, Bo Zhang

Bayesian neural networks (BNNs) introduce uncertainty estimation to deep networks by performing Bayesian inference on network weights.

Bayesian Inference Neural Architecture Search +1

Training Interpretable Convolutional Neural Networks towards Class-specific Filters

no code implementations25 Sep 2019 Haoyu Liang, Zhihao Ouyang, Hang Su, Yuyuan Zeng, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang

Convolutional neural networks (CNNs) have often been treated as “black-box” and successfully used in a range of tasks.

LIA: Latently Invertible Autoencoder with Adversarial Learning

no code implementations25 Sep 2019 Jiapeng Zhu, Deli Zhao, Bolei Zhou, Bo Zhang

A two-stage stochasticity-free training scheme is designed to train LIA via adversarial learning, in the sense that the decoder of LIA is first trained as a standard GAN with the invertible network and then the partial encoder is learned from an autoencoder by detaching the invertible network from LIA.

Generative Adversarial Network Variational Inference

Latent Variables on Spheres for Sampling and Inference

no code implementations25 Sep 2019 Deli Zhao, Jiapeng Zhu, Bo Zhang

Variational inference is a fundamental problem in Variational AutoEncoder (VAE).

Variational Inference

Document Rectification and Illumination Correction using a Patch-based CNN

1 code implementation20 Sep 2019 Xiaoyu Li, Bo Zhang, Jing Liao, Pedro V. Sander

We propose a novel learning method to rectify document images with various distortion types from a single input image.

Optical Character Recognition (OCR)

Blind Geometric Distortion Correction on Images Through Deep Learning

1 code implementation CVPR 2019 Xiaoyu Li, Bo Zhang, Pedro V. Sander, Jing Liao

We propose the first general framework to automatically correct different types of geometric distortion in a single input image.

Deriving the stellar labels of LAMOST spectra with Stellar LAbel Machine (SLAM)

1 code implementation23 Aug 2019 Bo Zhang, Chao Liu, Li-Cai Deng

To illustrate this capability, we test the performance of SLAM on stars ranging from Teff$\sim$4000 to $\sim$8000 K trained on LAMOST spectra and stellar labels.

Solar and Stellar Astrophysics Astrophysics of Galaxies Instrumentation and Methods for Astrophysics

Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos

no code implementations22 Aug 2019 Zihan Liu, Bo Huang, Yuqi Cui, Yifan Xu, Bo Zhang, Lixia Zhu, Yang Wang, Lei Jin, Dongrui Wu

Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.

General Classification

MoGA: Searching Beyond MobileNetV3

2 code implementations4 Aug 2019 Xiangxiang Chu, Bo Zhang, Ruijun Xu

Bearing the target hardware in mind, we propose the first Mobile GPU-Aware (MoGA) neural architecture search in order to be precisely tailored for real-world applications.

Image Classification Neural Architecture Search

Curriculum Learning for Deep Generative Models with Clustering

no code implementations27 Jun 2019 Deli Zhao, Jiapeng Zhu, Zhenfang Guo, Bo Zhang

The experiments on cat and human-face data validate that our algorithm is able to learn the optimal generative models (e. g. ProGAN) with respect to specified quality metrics for noisy data.

Clustering Generative Adversarial Network

Disentangled Inference for GANs with Latently Invertible Autoencoder

3 code implementations19 Jun 2019 Jiapeng Zhu, Deli Zhao, Bo Zhang, Bolei Zhou

In this paper, we show that the entanglement of the latent space for the VAE/GAN framework poses the main challenge for encoder learning.

Learning Semantic Vector Representations of Source Code via a Siamese Neural Network

no code implementations26 Apr 2019 David Wehr, Halley Fede, Eleanor Pence, Bo Zhang, Guilherme Ferreira, John Walczyk, Joseph Hughes

The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code.

BIG-bench Machine Learning

Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction

no code implementations22 Mar 2019 Dongyang Zhao, Liang Zhang, Bo Zhang, Lizhou Zheng, Yongjun Bao, Weipeng Yan

To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i. e., high-level agent and low-level agent.

Hierarchical Reinforcement Learning Recommendation Systems +2

A Matrix-in-matrix Neural Network for Image Super Resolution

1 code implementation19 Mar 2019 Hailong Ma, Xiangxiang Chu, Shaohua Wan, Bo Zhang

In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper layers.

Image Super-Resolution

Function Space Particle Optimization for Bayesian Neural Networks

1 code implementation ICLR 2019 Ziyu Wang, Tongzheng Ren, Jun Zhu, Bo Zhang

While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature.

Variational Inference

Artificial Intelligence in Intelligent Tutoring Robots: A Systematic Review and Design Guidelines

no code implementations26 Feb 2019 Jinyu Yang, Bo Zhang

We first analyse the environment of the ITR and propose a relationship model for describing interactions of ITR with the students, the social milieu and the curriculum.

Pairwise Teacher-Student Network for Semi-Supervised Hashing

no code implementations2 Feb 2019 Shifeng Zhang, Jianmin Li, Bo Zhang

Hashing method maps similar high-dimensional data to binary hashcodes with smaller hamming distance, and it has received broad attention due to its low storage cost and fast retrieval speed.

Retrieval

To Relieve Your Headache of Training an MRF, Take AdVIL

no code implementations ICLR 2020 Chongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang

We propose a black-box algorithm called {\it Adversarial Variational Inference and Learning} (AdVIL) to perform inference and learning on a general Markov random field (MRF).

Variational Inference

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