Papers › Understanding and Improving Early Stopping for Learning with Noisy Labels

Understanding and Improving Early Stopping for Learning with Noisy Labels

30 Jun 2021NeurIPS 2021 12arXiv:2106.15853archive 2025-07-28

Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, Tongliang Liu

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of training, is usually adopted. Current methods generally decide the early stopping point by considering a DNN as a whole. However, a DNN can be considered as a composition of a series of layers, and we find that the latter layers in a DNN are much more sensitive to label noise, while their former counterparts are quite robust. Therefore, selecting a stopping point for the whole network may make different DNN layers antagonistically affected each other, thus degrading the final performance. In this paper, we propose to separate a DNN into different parts and progressively train them to address this problem. Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs. During training, we progressively train the latter DNN layers by using a smaller number of epochs with the preceding layers fixed to counteract the impact of noisy labels. We term the proposed method as progressive early stopping (PES). Despite its simplicity, compared with the early stopping, PES can help to obtain more promising and stable results. Furthermore, by combining PES with existing approaches on noisy label training, we achieve state-of-the-art performance on image classification benchmarks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tmllab/PES officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationLearning with noisy labelsMemorizationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Learning with noisy labels CIFAR-10N-Aggregate PES (Semi) Accuracy (mean) 94.66 #9 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Early Stopping

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections