AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

PASS: Part-Aware Self-Supervised Pre-training for Person Re-identification

Kuan Zhu, Haiyun Guo, Tianyi Yan, Yousong Zhu, Jinqiao Wang, Ming Tang

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 97 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 [PART] tokens with part-aware matching (PASS) over DINOViT-S · MSMT17 (supervised)mAP: 64.2 -> 69.1Improved
add [PART] tokens (PASS) over DINOViT-S · Market1501 (supervised)mAP: 90.3 -> 92.2Improved
use PASS instead of DINO in UDA ReIDViT-S · Market2MSMT (UDA)mAP: 43.9 -> 49.1Improved
use PASS instead of DINO in USL ReIDViT-S · MSMT17 (USL)mAP: 38.4 -> 41.0Improved
use L=3 local areas instead of L=2 (ablation)PASS ViT-S · MSMT17 (supervised)mAP: 67.7 -> 69.1Improved
use L=3 local areas instead of L=5 (ablation)PASS ViT-S · MSMT17 (supervised)mAP: 67.3 -> 69.1Improved
use L=3 local areas instead of L=4 (ablation)PASS ViT-S · Market1501 (supervised)mAP: 91.9 -> 92.2Improved
use L=3 instead of multi-granularity L=2,3 (ablation)PASS ViT-S · MSMT17 (supervised)mAP: 68.7 -> 69.1Improved
concatenate [CLS] and mean [PART] instead of concatenating all tokens (ablation)PASS ViT-S · MSMT17 (supervised)mAP: 67.7 -> 69.1Improved
concatenate [CLS] and mean [PART] instead of the mean feature (ablation)PASS ViT-S · MSMT17 (supervised)mAP: 68.7 -> 69.1Improved
use mean feature instead of concatenating [CLS] and mean [PART] (ablation)PASS ViT-S · Market2MSMT (UDA)mAP: 44.9 -> 49.1Improved
use concatenation of [CLS] and mean [PART] instead of mean feature (ablation)PASS ViT-S · Market1501 (USL)Rank-1: 94.6 -> 94.9Mixed

Later papers that compared with this method

5 later accepted papers report PASS as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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