AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Part-Aware Transformer for Generalizable Person Re-identification

Hao Ni, Yuke Li, Lianli Gao, Heng Tao Shen, Jingkuan Song

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Generalizable person re-identification · 153 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
add conventional self-distillation to the baseline (ablation)TransReID-B/16 baseline · Market1501 -> DukeMTMCmAP: 46.5 -> 44.9Hurt
add Cross-ID Similarity Learning (CSL) (ablation)TransReID-B/16 baseline · Market1501 -> DukeMTMCmAP: 46.5 -> 48.3Improved
add Part-guided Self-Distillation on top of CSL (ablation)PAT · Market1501 -> MSMT17Rank-1: 40.2 -> 42.8Improved
add CSL+PSD to DeiT-Tiny backboneDeiT-Tiny · Market1501 -> DukeMTMCRank-1: 39.0 -> 48.5Improved
add CSL+PSD to ViT-Base backboneViT-Base · Market1501 -> DukeMTMCmAP: 46.5 -> 48.9Improved
use 3 parts instead of 2 (ablation)PAT · Market1501 -> DukeMTMCmAP: 47.0 -> 48.9Improved
use 3 parts instead of 5 (ablation)PAT · Market1501 -> DukeMTMCmAP: 47.9 -> 48.9Improved
pure Transformer PAT vs prior SOTA on multi-source M+D+C to MSMT17PAT · M+D+C -> MSMT17mAP: 14.7 -> 21.6Improved
PAT vs TransMatcher on Market -> MSMTPAT · Market1501 -> MSMT17Rank-1: 47.3 -> 42.8Hurt

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