AI Paper Atlas

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

Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization

Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin

ECCV 2022 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 57 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
replace small-loss selection with the fluctuation criterion (ablation)Co-teaching · CIFAR-10 (symmetric 80%)test accuracy (%): 34.6 -> 39.7Improved
replace small-loss selection with the fluctuation criterion (ablation)JoCoR · CIFAR-10 (symmetric 80%)test accuracy (%): 38.0 -> 41.6Improved
replace small-loss selection with the fluctuation criterionDivideMix · CIFAR-10 and CIFAR-100test accuracy (%): 93.4 -> 94.1 (CIFAR-10 pair 40%); 93.0 -> 92.8 (CIFAR-10 symmetric 80%)Mixed
replace small-loss selection with the fluctuation criterionDivideMix · CIFAR-100 (pair 40%)test accuracy (%): 71.0 -> 72.4Improved
add FixMatch semi-supervised learning on discarded samples (SFT+)SFT · CIFAR-10 (instance 40%)test accuracy (%): 89.97 -> 94.4Improved
add FixMatch semi-supervised learning on discarded samples (SFT+)SFT · CIFAR-100 (instance 40%)test accuracy (%): 69.91 -> 74.1Improved
use MixMatch instead of FixMatchSFT+ · CIFAR-10 / CIFAR-100 noise settingstest accuracy (%): 92.9 -> 93.7 (pair 40%); 94.4 -> 94.1 (instance 40%)Mixed
add warm-up and main-learning confidence regularizers R and L_CR (ablation)SFT · 40% noise ratiotest accuracy (%) and F-score: 3.72% accuracy and 0.023 F-score decrease when removedImproved
use fluctuation criterion instead of majority voting (ablation)SFT · noisy CIFARtest accuracy and F-scoreImproved
use larger confidence threshold Gamma (0.2 to 0.8) (ablation)SFT · CIFAR-10/100test accuracy (%)No clear effect
use larger memory bank size T (ablation)SFT · CIFAR-10/100test accuracy and F-scoreHurt
add MixMatch SSL (SFT+*) vs ELR+ on Clothing1MSFT+* · Clothing1Mtest accuracy (%): 0.27% improvement over ELR+Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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