AI Paper Atlas

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

CSOR: Coreset Selection for Object Re-identification via Class Pruning

Minyoung Oh, Jae-Young Sim

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification

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 diversity-driven class pruning (DCP) to random sampling (ablation)Random coreset · Market1501 (budget 1,000 images)mAP: 54.5 -> 58.0Improved
add coverage-prioritized sampling (CPS) with easy-to-hard class order (ablation)Random coreset · Market1501 (budget 500 images)mAP: 37.0 -> 54.1Improved
add DCP on top of CPS (ablation)CPS · Market1501 (budget 1,000 images)mAP: 64.3 -> 67.1Improved
add DCP on top of CPS at lowest budget (ablation)CPS · Market1501 (budget 500 images)mAP: 54.1 -> 54.8No clear effect
prioritize easy classes first instead of hard-to-easy (ablation)CSOR · Market1501 (budget 500 images)mAP: 44.2 -> 54.8Improved
use class-prioritized easy-to-hard allocation instead of sample-wise allocation (ablation)CSOR · Market1501 (budget 500 images)mAP: 14.8 -> 54.8Improved
use easy-to-hard class order instead of random class selection (ablation)CSOR · Market1501 (budget 1,000 images)mAP: 64.7 -> 67.1Improved
prune class with low diversity scores at ratio alpha about 0.2 (ablation)CSOR · Market1501mAPImproved
raise termination threshold tau from too small to 0.01 (ablation)CSOR · Market1501mAPImproved
use CSOR coreset instead of AUM coreset (ablation)SBS · Market1501 (budget 1,000 images)mAP: 31.8 -> 39.7Improved
use CSOR coreset instead of EL2N coresetSOLIDER · Market1501 (budget 1,500 images)mAP: 72.4 -> 76.0Improved
use CSOR coreset instead of AUM coresetCross-dataset MS->MA · Market1501 (trained on MSMT17, 1,000 images)mAP: 10.1 -> 35.3Improved

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