AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Deep Noise Label Learning via Effective Rank Reduction

Changyi Ma, Zihan Fang, Lihua Zhou, Tao Li, Wenyu Liu, Runsheng Yu, Xuan Song

ECCV 2026 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling

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 nuclear-norm effective-rank regularization on transition matrix (ablation)LENL · CIFAR-100Naccuracy: -4.6% accuracy when removedImproved
low-effective-rank transition matrix versus PLMLENL-NS · CIFAR-100Naccuracy: 60.52 -> 61.51Improved
LENL versus PLM/IDLE on CIFAR-100 synthetic noiseLENL-SVD · CIFAR-100accuracy: 69.54 -> 70.42 (Sym-20%)Improved
Newton-Schulz nuclear norm instead of SVD for large class countsLENL · ImageNet-1Kaccuracy: VolMinNet fails; LENL-NS 73.35 (Sym-20%)Improved
LENL-NS versus Co-Teaching on ImageNet-1KLENL-NS · ImageNet-1K Pair-45%accuracy: 64.08 -> 65.59Improved
LENL-NS versus CE on Food-101NLENL-NS · Food-101Naccuracy: 80.34 -> 83.30Improved
LENL-NS versus CE on Noisy Ostracods precisionLENL-NS · Noisy Ostracodsprecision: 88.50 -> 87.21No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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