AI Paper Atlas

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

Holistic Label Correction for Noisy Multi-Label Classification

Xiaobo Xia, Jiankang Deng, Wei Bao, Yuxuan Du, Bo Han, Shiguang Shan, Tongliang Liu

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 23 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 dependence to the holistic score (not only instance-label dependence) (ablation)HLC · Noisy Pascal-VOC 2007, Sym. 50%mAP: 67.06 -> 68.00Improved
add label dependence to the holistic score (ablation)HLC · Noisy Pascal-VOC 2012, Sym. 50%mAP: 67.88 -> 68.69Improved
add label dependence to the holistic score (ablation)HLC · Noisy MS-COCO, Sym. 50%mAP: 46.21 -> 48.15Improved
add holistic label correction on top of ADDGCN (ablation)ADDGCN · Noisy Pascal-VOC 2007, Sym. 50%mAP: 44.14 -> 68.00Improved
vary correction threshold delta in 0.25-0.45 (ablation)HLC · Noisy Pascal-VOC 2007 and 2012mAPNo clear effect
label correction (JOINT) vs no correction (APL, CDR)baselines · Noisy Pascal-VOC 2007, Sym. 50%mAP: JOINT 53.27 vs APL 47.64, CDR 49.12Improved
replace HLC with HLC+ASL lossHLC · NUS-WIDEmAP: 63.1 -> 64.5Improved
use HLC at small image size 112x112HLC · Noisy MS-COCO (112x112)mAP: 35.98 vs CCMN 36.17No clear effect
multi-label methods designed for clean labels (CSRA, ADDGCN) versus plain BCEnoisy multi-label training · Noisy Pascal-VOC 2007, Sym. 40%mAP: BCE 58.65 vs ADDGCN 55.75Hurt

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