activity
20132023
most citedAffinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

153 citations · 569 across the 23 of their papers we have counts for

collaborators
Showing 2018Show all

16 papers · 1 filter

cs.CV2018

STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification

Yang Fu, Xiaoyang Wang, Yunchao Wei +1

In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person re-identification task in videos. Different from the most existing metho…

cs.CV2018

Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

Rui Qian, Yunchao Wei, Honghui Shi +3

Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PD…

cs.CV2018

CCNet: Criss-Cross Attention for Semantic Segmentation

Zilong Huang, Xinggang Wang, Yunchao Wei +4

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-im…

cs.CV2018

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

Yang Fu, Yunchao Wei, Guanshuo Wang +3

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in th…

cs.CV2018

A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization

Bowen Cheng, Yunchao Wei, Jiahui Yu +5

While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in…

cs.CV2018

Self-Erasing Network for Integral Object Attention

Qibin Hou, Peng-Tao Jiang, Yunchao Wei +1

Recently, adversarial erasing for weakly-supervised object attention has been deeply studied due to its capability in localizing integral object regions. However, such a strategy r…