activity
20162024
most citedMetaFormer Baselines for Vision

297 citations · 1.2k across the 113 of their papers we have counts for

collaborators
Showing 2021Show all

20 papers · 1 filter

cs.CV2021

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

Jue Wang, Shaoli Huang, Xinchao Wang +1

Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning…

cs.CR2021

Safe Distillation Box

Jingwen Ye, Yining Mao, Jie Song +3

Knowledge distillation (KD) has recently emerged as a powerful strategy to transfer knowledge from a pre-trained teacher model to a lightweight student, and has demonstrated its un…

math.GR2021

A further generalization of the Glauberman-Thompson -nilpotency criterion in fusion systems

Zhencai Shen, Baoyu Zhang

Let be a prime and be a saturated fusion system over a finite -group . The fusion system is said to be nilpotent if $\mathcal{F}=\mathcal{F}_{…

cs.CV2021

Shunted Self-Attention via Multi-Scale Token Aggregation

Sucheng Ren, Daquan Zhou, Shengfeng He +2

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of…

cs.CV2021

MetaFormer Is Actually What You Need for Vision

Weihao Yu, Mi Luo, Pan Zhou +5

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent…

cs.CV2021

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

Xin Jin, Tianyu He, Xu Shen +5

Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering…