activity
20162024
most citedSegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

487 citations · 2.1k across the 38 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

9 papers · 2 filters

cs.CV2021★ 23 cited

VOLO: Vision Outlooker for Visual Recognition

Li Yuan, Qibin Hou, Zihang Jiang +2

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of sel…

cs.CV2021★ 25 cited

Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition

Qibin Hou, Zihang Jiang, Li Yuan +3

In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional in…

cs.CV2021★ 41 cited

Refiner: Refining Self-attention for Vision Transformers

Daquan Zhou, Yujun Shi, Bingyi Kang +6

Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most…

cs.CV2021★ 349 cited

DeepViT: Towards Deeper Vision Transformer

Daquan Zhou, Bingyi Kang, Xiaojie Jin +5

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be…

cs.CV2021

All Tokens Matter: Token Labeling for Training Better Vision Transformers

Zihang Jiang, Qibin Hou, Li Yuan +5

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViT…

cs.CV2021

AutoSpace: Neural Architecture Search with Less Human Interference

Daquan Zhou, Xiaojie Jin, Xiaochen Lian +4

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automati…