activity
20192022
most citedHRFormer: High-Resolution Transformer for Dense Prediction

128 citations · 148 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20222 cited

Learning Where to Learn in Cross-View Self-Supervised Learning

Lang Huang, Shan You, Mingkai Zheng +3

Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection…

cs.CV2022

SimMatch: Semi-supervised Learning with Similarity Matching

Mingkai Zheng, Shan You, Lang Huang +3

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised le…

cs.CV2021128 cited

HRFormer: High-Resolution Transformer for Dense Prediction

Yuhui Yuan, Rao Fu, Lang Huang +4

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that prod…

cs.LG2020

Self-Adaptive Training: beyond Empirical Risk Minimization

Lang Huang, Chao Zhang, Hongyang Zhang

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost--…

cs.CV201918 cited

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

Jianyuan Guo, Yuhui Yuan, Lang Huang +3

Person re-identification is a challenging task due to various complex factors. Recent studies have attempted to integrate human parsing results or externally defined attributes to…

cs.CV2019

Interlaced Sparse Self-Attention for Semantic Segmentation

Lang Huang, Yuhui Yuan, Jianyuan Guo +3

In this paper, we present a so-called interlaced sparse self-attention approach to improve the efficiency of the \emph{self-attention} mechanism for semantic segmentation. The main…