Papers › MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels

MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels

14 Dec 2017ICML 2018 7arXiv:1712.05055archive 2025-07-28

Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, Li Fei-Fei

Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet, to supervise the training of the base deep networks, namely, StudentNet. During training, MentorNet provides a curriculum (sample weighting scheme) for StudentNet to focus on the sample the label of which is probably correct. Unlike the existing curriculum that is usually predefined by human experts, MentorNet learns a data-driven curriculum dynamically with StudentNet. Experimental results demonstrate that our approach can significantly improve the generalization performance of deep networks trained on corrupted training data. Notably, to the best of our knowledge, we achieve the best-published result on WebVision, a large benchmark containing 2.2 million images of real-world noisy labels. The code are at https://github.com/google/mentornet

PaperPDFConference PDFCode

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

Code

google/mentornet officialmentioned in papermentioned on GitHubtf 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 Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification WebVision-1000 MentorNet (InceptionResNet-V2) ImageNet Top-1 Accuracy 62.5% #16 of 16 Archive leaderboard report
Image Classification WebVision-1000 MentorNet (InceptionResNet-V2) ImageNet Top-5 Accuracy 83.0% #16 of 16 Archive leaderboard report
Image Classification WebVision-1000 MentorNet (InceptionResNet-V2) Top-1 Accuracy 70.8% #16 of 16 Archive leaderboard report
Image Classification WebVision-1000 MentorNet (InceptionResNet-V2) Top-5 Accuracy 88.0% #16 of 16 Archive leaderboard report
Image Classification mini WebVision 1.0 MentorNet (Inception-ResNet-v2) ImageNet Top-1 Accuracy 63.8 #44 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 MentorNet (Inception-ResNet-v2) ImageNet Top-5 Accuracy 85.8 #44 of 47 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