AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Implicit Sample Extension for Unsupervised Person Re-Identification

Xinyu Zhang, Dongdong Li, Zhigang Wang, Jian Wang, Errui Ding, Javen Qinfeng Shi, Zhaoxiang Zhang, Jingdong Wang

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 139 citations (OpenAlex)

Check 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 progressive linear interpolation support samples (ablation)Cluster-Contrast baseline · Market-1501mAP: 82.5 -> 83.9Improved
Add progressive linear interpolation support samples (ablation)Cluster-Contrast baseline · MSMT17mAP: 30.1 -> 33.5Improved
Add label-preserving loss on support samples (ablation)ISE with PLI · Market-1501mAP: 83.9% to 84.7%Improved
Add label-preserving loss on support samples (ablation)ISE with PLI · MSMT17mAP: 33.5% to 35.0%Improved
Add logarithmically progressive rather than constant support-sample degree (ablation)ISE with PLI and LP · Market-1501mAP: 83.3 -> 84.7Improved
Add logarithmically progressive rather than constant support-sample degree (ablation)ISE with PLI and LP · MSMT17mAP: 33.8 -> 35.0Improved
Use logarithmic rather than square degree schedule (ablation)ISE · MSMT17mAP: 32.4 -> 35.0Improved
Use nearest-cluster rather than random direction (ablation)ISE · MSMT17mAP: 28.3 -> 35.0Improved
Use nearest-cluster rather than farthest direction (ablation)ISE · MSMT17mAP: 27.8 -> 35.0Improved
Increase nearest clusters from K=1 to K=5 (ablation)ISE · Market-1501mAP: 84.7 -> 84.8Improved
Increase nearest clusters from K=1 to K=5 (ablation)ISE · MSMT17mAP: 35.0 -> 31.9Hurt
Add GeM poolingISE · MSMT17mAP: 35.0 -> 37.0Improved

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