Xinchao Wang

Disassembling Object Representations without Labels

In this paper, we study a new representation-learning task, which we ter...
04/03/2020 ∙ by Zunlei Feng, et al. ∙ 0 ∙ share

read it
Learning Oracle Attention for High-fidelity Face Completion

High-fidelity face completion is a challenging task due to the rich and ...
03/31/2020 ∙ by Tong Zhou, et al. ∙ 0 ∙ share

read it
Distillating Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...
03/23/2020 ∙ by Yiding Yang, et al. ∙ 70 ∙ share

read it
Distilling Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...
03/23/2020 ∙ by Yiding Yang, et al. ∙ 0 ∙ share

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

Recent advances in deep learning have provided procedures for learning o...
03/20/2020 ∙ by Jingwen Ye, et al. ∙ 0 ∙ share

read it
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability

Exploring the intrinsic interconnections between the knowledge encoded i...
03/17/2020 ∙ by Jie Song, et al. ∙ 0 ∙ share

read it
Data-Free Adversarial Distillation

Knowledge Distillation (KD) has made remarkable progress in the last few...
12/23/2019 ∙ by Gongfan Fang, et al. ∙ 13 ∙ share

read it
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers

Lip reading has witnessed unparalleled development in recent years thank...
11/26/2019 ∙ by Ya Zhao, et al. ∙ 0 ∙ share

read it
Dynamic Instance Normalization for Arbitrary Style Transfer

Prior normalization methods rely on affine transformations to produce ar...
11/16/2019 ∙ by Yongcheng Jing, et al. ∙ 0 ∙ share

read it
Deep Model Transferability from Attribution Maps

Exploring the transferability between heterogeneous tasks sheds light on...
09/26/2019 ∙ by Jie Song, et al. ∙ 12 ∙ share

read it
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation

A massive number of well-trained deep networks have been released by dev...
08/20/2019 ∙ by Chengchao Shen, et al. ∙ 0 ∙ share

read it
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning

An increasing number of well-trained deep networks have been released on...
06/24/2019 ∙ by Sihui Luo, et al. ∙ 0 ∙ share

read it
One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation

Class imbalance has been one of the major challenges for medical image s...
06/05/2019 ∙ by Chenhong Zhou, et al. ∙ 0 ∙ share

read it
Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers

Many well-trained Convolutional Neural Network(CNN) models have now been...
05/28/2019 ∙ by Jingwen Ye, et al. ∙ 0 ∙ share

read it
Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts

Not all the human body parts have the same degree of freedom (DOF) due t...
05/20/2019 ∙ by Jue Wang, et al. ∙ 0 ∙ share

read it
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More

In this paper, we investigate a novel deep-model reusing task. Our goal ...
04/23/2019 ∙ by Jingwen Ye, et al. ∙ 0 ∙ share

read it
A Light Dual-Task Neural Network for Haze Removal

Single-image dehazing is a challenging problem due to its ill-posed natu...
04/12/2019 ∙ by Yu Zhang, et al. ∙ 0 ∙ share

read it
Amalgamating Knowledge towards Comprehensive Classification

With the rapid development of deep learning, there have been an unpreced...
11/07/2018 ∙ by Chengchao Shen, et al. ∙ 0 ∙ share

read it
Wide Activation for Efficient and Accurate Image Super-Resolution

In this report we demonstrate that with same parameters and computationa...
08/27/2018 ∙ by Jiahui Yu, et al. ∙ 0 ∙ share

read it
Dual Swap Disentangling

Learning interpretable disentangled representations is a crucial yet cha...
05/27/2018 ∙ by Zunlei Feng, et al. ∙ 0 ∙ share

read it
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks

Discriminative features are critical for machine learning applications. ...
04/22/2018 ∙ by Fusheng Hao, et al. ∙ 0 ∙ share

read it
Horizontal Pyramid Matching for Person Re-identification

Despite the remarkable recent progress, person Re-identification (Re-ID)...
04/14/2018 ∙ by Yang Fu, et al. ∙ 0 ∙ share

read it
Deep Motion Boundary Detection

Motion boundary detection is a crucial yet challenging problem. Prior me...
04/13/2018 ∙ by Xiaoqing Yin, et al. ∙ 0 ∙ share

read it
FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification

Images captured by fisheye lenses violate the pinhole camera assumption ...
04/13/2018 ∙ by Xiaoqing Yin, et al. ∙ 0 ∙ share

read it
A Performance Evaluation of Local Features for Image Based 3D Reconstruction

This paper performs a comprehensive and comparative evaluation of the st...
12/14/2017 ∙ by Bin Fan, et al. ∙ 0 ∙ share

read it
Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids

In this paper, we propose gated recurrent feature pyramid for the proble...
12/04/2017 ∙ by Zhiqiang Shen, et al. ∙ 0 ∙ share

read it
Globally Consistent Multi-People Tracking using Motion Patterns

Many state-of-the-art approaches to people tracking rely on detecting th...
12/02/2016 ∙ by Andrii Maksai, et al. ∙ 0 ∙ share

read it
Do We Need Binary Features for 3D Reconstruction?

Binary features have been incrementally popular in the past few years du...
02/14/2016 ∙ by Bin Fan, et al. ∙ 0 ∙ share

read it
Predicting People's 3D Poses from Short Sequences

We propose an efficient approach to exploiting motion information from c...
04/30/2015 ∙ by Bugra Tekin, et al. ∙ 0 ∙ share

read it
Globally Optimal Cell Tracking using Integer Programming

We propose a novel approach to automatically tracking cell populations i...
01/22/2015 ∙ by Engin Türetken, et al. ∙ 0 ∙ share

read it

Xinchao Wang

Featured Co-authors