AI Paper Atlas

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

RML++: Regroup Median Loss for Combating Label Noise

Fengpeng Li, Kemou Li, Qizhou Wang, Bo Han, Jinyu Tian, Jiantao Zhou

IJCV 2025 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 3 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 loss processing for sample selection (ablation)RML · CIFAR-10 instance-0.4accuracy (%): 88.47 -> 90.73Improved
add loss processing for sample selection (ablation)RML · CIFAR-100 instance-0.4accuracy (%): 65.43 -> 71.12Improved
add loss processing for sample selection (ablation)RML · CIFAR-100 pairflip-0.45accuracy (%): 56.36 -> 64.67Improved
use median operation instead of mean loss (ablation)RML · CIFAR-10 instance-0.4accuracy (%): 85.32 -> 90.73Improved
increase median window size n from 2 to 6 (ablation)RML · CIFAR-10 instance-0.4accuracy (%): 87.41 -> 90.73Improved
increase window size n from 6 to 10 (ablation)RML · CIFAR-10 instance-0.4accuracy (%): 90.73 -> 89.71Hurt
use RML instead of PESResNet · CIFAR-100 sym-0.5accuracy (%): 58.90 -> 67.05Improved
use RML instead of PESResNet · CIFAR-10 sym-0.2accuracy (%): 92.38 -> 92.89Improved
add semi-supervised strategy (MixMatch) to RMLRML · WebVisionaccuracy (%): 73.32 -> 81.34Improved
use RML-Semi instead of PESResNet-50 · Clothing1Maccuracy (%): 74.99 -> 75.14Improved

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