AI Paper Atlas

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

Distributionally Robust Loss for Long-Tailed Multi-Label Image Classification

Dekun Lin, Zhe Cui, Rui Chen, Tailai Peng, xinran xie, Xiaolin Qin

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 8 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
compute LSEP class-wise (C-LSEP) instead of per sample (ablation)LSEP · VOC-LTtotal mAP: 72.99 -> 74.93Improved
compute LSEP class-wise (C-LSEP) instead of per sample (ablation)LSEP · COCO-LTtotal mAP: 47.05 -> 50.35Improved
add negative gradient constraint (NGC) to C-LSEP (ablation)C-LSEP · VOC-LTtotal mAP: 74.93 -> 78.01Improved
add negative gradient constraint (NGC) to C-LSEP (ablation)C-LSEP · COCO-LTtotal mAP: 50.35 -> 54.10Improved
add positive gradient constraint (PGC) to C-LSEP (ablation)C-LSEP · VOC-LTtotal mAP: 74.93 -> 74.74Hurt
add PGC on top of NGC (GC) to C-LSEP (ablation)C-LSEP + NGC · VOC-LTtotal mAP: 78.01 -> 76.90Hurt
add PGC on top of NGC (GC) to C-LSEP (ablation)C-LSEP + NGC · COCO-LTtotal mAP: 54.10 -> 53.58Hurt
compute ZLPR class-wise (C-ZLPR) (ablation)ZLPR · COCO-LTtotal mAP: 49.90 -> 51.76Improved
combine DR loss with DB Focal (ablation)DR Loss · VOC-LTtotal mAP: 78.01 -> 78.75Improved
combine DR loss with DB Focal (ablation)DR Loss · COCO-LTtotal mAP: 54.10 -> 54.55Improved
combine baseline C-LSEP with DB Focal (ablation)DB Focal · VOC-LTtotal mAP: 78.17 -> 76.21Hurt
combine BCE with DR loss (ablation)DR Loss · COCO-LTtotal mAP: 54.10 -> 52.84Hurt

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