AI Paper Atlas

Research map / 3D vision / Human pose estimation

ViTPose++: Vision Transformer for Generic Body Pose Estimation

Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao

TPAMI 2023 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 217 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use simple decoder instead of classic decoder with ResNet-50 (ablation)SimpleBaseline ResNet-50 · MS COCO valAP: 71.8 -> 53.1Hurt
use simple decoder instead of classic decoder with ViT backbone (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 75.5No clear effect
use minimal decoder (single linear layer) (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 75.4No clear effect
replace random init with MAE pre-training (ablation)ViTPose-B · MS COCO valAP: 72.8 -> 75.8Improved
replace MAE with supervised DeiT or contrastive MoCov3 pre-training (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 72.7 (DeiT), 72.1 (MoCov3)Hurt
increase input resolution from 256x192 to 576x432 (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 77.8Improved
1/8 feature size with full attention instead of window attention without shift (ablation)ViTPose-B · MS COCO valAP: 66.4 -> 77.4Improved
add shift windows to window attention (ablation)ViTPose-B 1/8 feature · MS COCO valAP: 66.4 -> 76.4Improved
freeze FFN during fine-tuning (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 72.8Hurt
freeze MHSA during fine-tuning (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 75.1Hurt
add knowledge token distillation from ViTPose-L (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 76.0Improved
add output (heatmap) distillation from ViTPose-L (ablation)ViTPose-B · MS COCO valAP: 75.8 -> 76.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy