AI Paper Atlas

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

Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels

Wenqiao Zhang, Changshuo Liu, Lingze Zeng, Bengchin Ooi, Siliang Tang, Yueting Zhuang

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 29 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 label correction (RLC) (ablation)COMIC · PLT-COCOTotal mAP: 54.70 -> 55.08Improved
add multi-focal modifier loss (ablation)COMIC · PLT-COCOTotal mAP: 54.60 -> 55.08Improved
add head-tail balancer (ablation)COMIC · PLT-COCOTotal mAP: 53.65 -> 55.08Improved
add positive-negative factor to MFM (on top of H-T) (ablation)MFM loss · PLT-COCOTotal Shot mAP: 54.44 -> 55.08Improved
add head-tail factor to MFM (on top of P-N) (ablation)MFM loss · PLT-COCOLow Shot mAP: 52.91 -> 55.36Improved
use dynamic instead of static class distribution for corrected-label weighting (ablation)RLC · PLT-COCOTotal Shot mAP: 54.67 -> 55.08Improved
decrease label missing ratio from 50% to 0% (ablation)COMIC · PLT-COCOTotal Shot mAP: 54.69 -> 57.07Improved
joint training of head, tail and balanced models versus detached (ablation)COMIC · PLT-COCOTotal mAPMixed
treat unannotated labels as negatives with BCE under LT and partial labelsBCE baseline · PLT-COCOTotal Shot mAP: 48.92 vs COMIC 55.08Hurt
use PL-MLC methods versus LT-MLC methodsbaselines · PLT-COCOmAPHurt

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