Papers › SELFIE: Refurbishing Unclean Samples for Robust Deep Learning

SELFIE: Refurbishing Unclean Samples for Robust Deep Learning

15 Jun 2019archive 2025-07-28

Hwanjun Song, Minseok Kim, Jae-Gil Lee

Owing to the extremely high expressive power of deep neural networks, their side effect is to totally memorize training data even when the labels are extremely noisy. To overcome overfitting on the noisy labels, we propose a novel robust training method called SELFIE. Our key idea is to selectively refurbish and exploit unclean samples that can be corrected with high precision, thereby gradually increasing the number of available training samples. Taking advantage of this design, SELFIE effectively prevents the risk of noise accumulation from the false correction and fully exploits the training data. To validate the superiority of SELFIE, we conducted extensive experimentation using four real-world or synthetic data sets. The result showed that SELFIE remarkably improved absolute test error compared with two state-of-the-art methods.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

kaist-dmlab/SELFIE mentioned in papertfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Very Deep Convolutional Networks for Large-Scale Image Recognition (arXiv:1409.1556; that paper's own run record: 81 ran (of which 0 constructed an object rather than computing a result; 69 with no instrument failure: 0 honoured, 0 violated, 69 with no contract checked; 12 where Syntology's instrument failed) · 41 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Deep LearningImage ClassificationLearning with noisy labels

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Learning with noisy labels ANIMAL SELFIE Accuracy 81.8 #16 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL SELFIE ImageNet Pretrained NO #16 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL SELFIE Network Vgg19-BN #16 of 19 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.

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