AI Paper Atlas

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

Me-Momentum: Extracting Hard Confident Examples From Noisily Labeled Data

Yingbin Bai, Tongliang Liu

ICCV 2021 · Label-efficient and robust learning › Noisy labels · approach: Loss correction and noise robustness theory · 32 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
re-initialize the classifier in an outer loop while keeping extracted confident examples (ablation)Me-Momentum · CIFAR10 and CIFAR100 noisy labelslabel precision of confident examples: label precision increases significantly after re-initializationImproved
add inner-loop alternating refinement of classifier and confident examples (ablation)Me-Momentum · CIFAR10, CIFAR100number of confident examples and test accuracy: accuracy and number increase, label precision decreases slightlyMixed
use the proposed slope-based early stopping instead of highest noisy validation accuracy for initialization (ablation)Me-Momentum step 1 · CIFAR10stopping epoch / noise fitted: stops earlier and fits less noiseImproved
vary early-stopping threshold tau over 0.05, 0.07, 0.1, 0.3, 0.5 (ablation)Me-Momentum · CIFAR10accuracy: robust to tau in 0.05 to 0.5No clear effect
use noisy validation data instead of clean validation data (ablation)Me-Momentum (pre-trained) · Clothing1Maccuracy: 75.18% -> 73.13%Hurt
pre-train ResNet-50 on ImageNet instead of random initialization (ablation)Me-Momentum · Clothing1M (clean val)accuracy: 74.75% -> 75.18%Improved
replace T-revision with Me-MomentumT-revision · Clothing1Maccuracy: 74.18% -> 75.18%Improved
replace CDR with Me-MomentumCDR · CIFAR100 Sym-40%accuracy: 60.18% -> 63.48%Improved
replace T-revision with Me-MomentumT-revision · CIFAR10 Inst-40%accuracy: 85.37% -> 86.66%Improved
replace DMI with Me-MomentumDMI · MNIST Sym-20%accuracy: 98.92% -> 98.94%No clear effect
replace DMI with Me-MomentumDMI · MNIST Inst-40%accuracy: 97.58% -> 98.11%Improved

Later papers that compared with this method

4 later accepted papers report Me-Momentum as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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