b'Xinchao Wang'

research

∙ 08/01/2022

AvatarGen: a 3D Generative Model for Animatable Human Avatars

Unsupervised generation of clothed virtual humans with various appearanc...

Jianfeng Zhang, et al. ∙

research

∙ 07/27/2022

Federated Selective Aggregation for Knowledge Amalgamation

In this paper, we explore a new knowledge-amalgamation problem, termed F...

Donglin Xie, et al. ∙

research

∙ 07/24/2022

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

Anomaly detection aims at identifying deviant samples from the normal da...

Gaoang Wang, et al. ∙

research

∙ 07/24/2022

Learning Graph Neural Networks for Image Style Transfer

State-of-the-art parametric and non-parametric style transfer approaches...

Yongcheng Jing, et al. ∙

research

∙ 07/17/2022

Learning with Recoverable Forgetting

Life-long learning aims at learning a sequence of tasks without forgetti...

Jingwen Ye, et al. ∙

research

∙ 07/13/2022

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

One key challenge of exemplar-guided image generation lies in establishi...

Songhua Liu, et al. ∙

research

∙ 07/05/2022

Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework

Despite the promising results achieved, state-of-the-art interactive rei...

Shunyu Liu, et al. ∙

research

∙ 07/04/2022

Factorizing Knowledge in Neural Networks

In this paper, we explore a novel and ambitious knowledge-transfer task,...

Xingyi Yang, et al. ∙

research

∙ 06/14/2022

Slimmable Domain Adaptation

Vanilla unsupervised domain adaptation methods tend to optimize the mode...

Rang Meng, et al. ∙

research

∙ 06/13/2022

Learning Domain Adaptive Object Detection with Probabilistic Teacher

Self-training for unsupervised domain adaptive object detection is a cha...

Meilin Chen, et al. ∙

research

∙ 05/23/2022

Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction

How to accurately predict the properties of molecules is an essential pr...

Kuangqi Zhou, et al. ∙

research

∙ 05/23/2022

FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

Face recognition, as one of the most successful applications in artifici...

Kai Wang, et al. ∙

research

∙ 05/16/2022

Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt

Data-free knowledge distillation (DFKD) conducts knowledge distillation ...

Xinyin Ma, et al. ∙

research

∙ 04/30/2022

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Learning with noisy labels has aroused much research interest since data...

Kai Wang, et al. ∙

research

∙ 03/29/2022

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision

Existing self-supervised 3D human pose estimation schemes have largely r...

Kehong Gong, et al. ∙

research

∙ 03/25/2022

Point2Seq: Detecting 3D Objects as Sequences

We present a simple and effective framework, named Point2Seq, for 3D obj...

Yujing Xue, et al. ∙

research

∙ 03/03/2022

CAFE: Learning to Condense Dataset by Aligning Features

Dataset condensation aims at reducing the network training effort throug...

Kai Wang, et al. ∙

research

∙ 12/21/2021

PONet: Robust 3D Human Pose Estimation via Learning Orientations Only

Conventional 3D human pose estimation relies on first detecting 2D body ...

Jue Wang, et al. ∙

research

∙ 12/12/2021

Up to 100x Faster Data-free Knowledge Distillation

Data-free knowledge distillation (DFKD) has recently been attracting inc...

Gongfan Fang, et al. ∙

research

∙ 12/05/2021

Safe Distillation Box

Knowledge distillation (KD) has recently emerged as a powerful strategy ...

Jingwen Ye, et al. ∙

research

∙ 11/30/2021

Shunted Self-Attention via Multi-Scale Token Aggregation

Recent Vision Transformer (ViT) models have demonstrated encouraging res...

Sucheng Ren, et al. ∙

research

∙ 11/22/2021

MetaFormer is Actually What You Need for Vision

Transformers have shown great potential in computer vision tasks. A comm...

Weihao Yu, et al. ∙

research

∙ 11/19/2021

Meta Clustering Learning for Large-scale Unsupervised Person Re-identification

Unsupervised Person Re-identification (U-ReID) with pseudo labeling rece...

Xin Jin, et al. ∙

research

∙ 10/27/2021

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Knowledge distillation (KD) aims to craft a compact student model that i...

Gongfan Fang, et al. ∙

research

∙ 10/27/2021

MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition

Multimodal emotion recognition study is hindered by the lack of labelled...

Jinming Zhao, et al. ∙

research

∙ 09/27/2021

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

In this paper, we study a novel meta aggregation scheme towards binarizi...

Yongcheng Jing, et al. ∙

research

∙ 08/16/2021

Structure-Aware Feature Generation for Zero-Shot Learning

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by lev...

Lianbo Zhang, et al. ∙

research

∙ 08/01/2021

Boundary Knowledge Translation based Reference Semantic Segmentation

Given a reference object of an unknown type in an image, human observers...

Lechao Cheng, et al. ∙

research

∙ 08/01/2021

Edge-competing Pathological Liver Vessel Segmentation with Limited Labels

The microvascular invasion (MVI) is a major prognostic factor in hepatoc...

Zunlei Feng, et al. ∙

research

∙ 08/01/2021

Visual Boundary Knowledge Translation for Foreground Segmentation

When confronted with objects of unknown types in an image, humans can ef...

Zunlei Feng, et al. ∙

research

∙ 06/07/2021

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Multi-person pose estimation and tracking serve as crucial steps for vid...

Yiding Yang, et al. ∙

research

∙ 05/18/2021

Contrastive Model Inversion for Data-Free Knowledge Distillation

Model inversion, whose goal is to recover training data from a pre-train...

Gongfan Fang, et al. ∙

research

∙ 05/10/2021

KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation

Knowledge distillation (KD) has recently emerged as an efficacious schem...

Mengqi Xue, et al. ∙

research

∙ 04/01/2021

Online Multiple Object Tracking with Cross-Task Synergy

Modern online multiple object tracking (MOT) methods usually focus on tw...

Song Guo, et al. ∙

research

∙ 02/28/2021

Training Generative Adversarial Networks in One Stage

Generative Adversarial Networks (GANs) have demonstrated unprecedented s...

Chengchao Shen, et al. ∙

research

∙ 01/10/2021

SPAGAN: Shortest Path Graph Attention Network

Graph convolutional networks (GCN) have recently demonstrated their pote...

Yiding Yang, et al. ∙

research

∙ 12/10/2020

Overcoming Catastrophic Forgetting in Graph Neural Networks

Catastrophic forgetting refers to the tendency that a neural network "fo...

Huihui Liu, et al. ∙

research

∙ 12/09/2020

Progressive Network Grafting for Few-Shot Knowledge Distillation

Knowledge distillation has demonstrated encouraging performances in deep...

Chengchao Shen, et al. ∙

research

∙ 12/09/2020

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Data mixing augmentation has proved effective in training deep models. R...

Shaoli Huang, et al. ∙

research

∙ 10/14/2020

Learning Propagation Rules for Attribution Map Generation

Prior gradient-based attribution-map methods rely on handcrafted propaga...

Yiding Yang, et al. ∙

research

∙ 10/12/2020

Factorizable Graph Convolutional Networks

Graphs have been widely adopted to denote structural connections between...

Yiding Yang, et al. ∙

research

∙ 07/18/2020

Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets

State-of-the-art multi-object tracking (MOT) methods follow the tracking...

Weihong Ren, et al. ∙

research

∙ 07/10/2020

Impression Space from Deep Template Network

It is an innate ability for humans to imagine something only according t...

Gongfan Fang, et al. ∙

research

∙ 04/03/2020

Disassembling Object Representations without Labels

In this paper, we study a new representation-learning task, which we ter...

Zunlei Feng, et al. ∙

research

∙ 03/31/2020

Learning Oracle Attention for High-fidelity Face Completion

High-fidelity face completion is a challenging task due to the rich and ...

Tong Zhou, et al. ∙

research

∙ 03/23/2020

Distillating Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...

Yiding Yang, et al. ∙

research

∙ 03/23/2020

Distilling Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...

Yiding Yang, et al. ∙

research

∙ 03/20/2020

Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN

Recent advances in deep learning have provided procedures for learning o...

Jingwen Ye, et al. ∙

research

∙ 03/17/2020

DEPARA: Deep Attribution Graph for Deep Knowledge Transferability

Exploring the intrinsic interconnections between the knowledge encoded i...

Jie Song, et al. ∙

research

∙ 12/23/2019

Data-Free Adversarial Distillation

Knowledge Distillation (KD) has made remarkable progress in the last few...

Gongfan Fang, et al. ∙

Xinchao Wang

Featured Co-authors