AI Paper Atlas

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

Towards Reliable Multi-Label Classification via Conditional Dependency Modeling

Arkapal Panda, Aditya Shankar Pal, Utpal Garain

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 0 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 the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · PASCAL VOC 2012ACE: 0.1533 -> 0.1265Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ViT-B/32) · PASCAL VOC 2012ACE: 0.0824 -> 0.0247Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · MS-COCOACE: 0.0654 -> 0.0030Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ViT-B/32) · MS-COCOACE: 0.0829 -> 0.0020Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · WIDER-AACE: 0.1352 -> 0.1232Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ViT-B/32) · WIDER-AACE: 0.0795 -> 0.0145Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ViT-B/32) · PASCAL VOC 2012MCE: 0.2346 -> 0.0761Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · MS-COCOMCE: 0.1766 -> 0.0052Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ViT-B/32) · MS-COCOmAP: 0.9207 -> 0.9775Improved
add the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · PASCAL VOC 2012mAP: 0.9025 -> 0.9251No clear effect
add the PCD auxiliary loss to BCE (CMLL)BCE (ResNet-50) · WIDER-AmAP: 0.8198 -> 0.8248No clear effect
vary the number of bins used to compute ACE and MCECMLL · PASCAL VOC 2012, MS-COCO, WIDER-AACE/MCENo clear effect

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