AI Paper Atlas

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

Scalable Penalized Regression for Noise Detection in Learning With Noisy Labels

Yikai Wang, Xinwei Sun, Yanwei Fu

CVPR 2022 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 39 citations (OpenAlex)

Check 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
Use SPR noisy-sample selection and train on selected clean dataC2F2 · MNIST, symmetric noise rates 0.2–0.8accuracy: 99.3 vs 99.2; 99.2 vs 99.2; 99.2 vs 98.9; 98.7 vs 98.0Improved
Use SPR noisy-sample selection with the full training frameworkResNet-18 · CIFAR-10, symmetric noise rates 0.2–0.8accuracy: 93.2 vs 90.2; 91.0 vs 87.2; 82.7 vs 80.5; 64.1 vs 45.7Improved
Use SPR noisy-sample selection with the full training frameworkResNet-18 · CIFAR-10, asymmetric noise rates 0.2–0.4accuracy: 92.8 vs 90.5; 91.3 vs 89.7; 89.0 vs 87.9Improved
Use SPR noisy-sample selectionVGG19-BN · ANIMAL10accuracy: 86.8 vs 84.1Improved
Use SPR noisy-sample selectionInception-ResNet · WebVisionaccuracy: 78.12 vs 77.32Improved
Add SPR detection and train with CE only on detected clean data (ablation)CE training · CIFAR-10, symmetric noise 0.4accuracy: 65.5 -> 80.4Improved
Add the ℓq penalty to CE on all training data (ablation)CE training · CIFAR-10, symmetric noise 0.4accuracy: 65.5 -> 71.6Improved
Apply CutMix to all training data (ablation)CE training · CIFAR-10, symmetric noise 0.4accuracy: 65.5 -> 87.0Improved
Add the ℓq penalty to CE + SPR (ablation)CE + SPR · CIFAR-10, symmetric noise 0.4accuracy: 80.4 -> 88.5Improved
Add CutMix to CE + SPR (ablation)CE + SPR · CIFAR-10, symmetric noise 0.4accuracy: 80.4 -> 89.2Improved
Add CutMix to CE + SPR + ℓq (ablation)Full SPR · CIFAR-10, symmetric noise 0.4accuracy: 88.5 -> 91.0Improved
Add the ℓq penalty to CE + SPR + CutMix (ablation)Full SPR · CIFAR-10, symmetric noise 0.4accuracy: 89.2 -> 91.0Improved

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