Papers › How does Disagreement Help Generalization against Label Corruption?
How does Disagreement Help Generalization against Label Corruption?
Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor W. Tsang, Masashi Sugiyama
Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural networks using the small-loss trick. However, with the increase of epochs, two networks converge to a consensus and Co-teaching reduces to the self-training MentorNet. To tackle this issue, we propose a robust learning paradigm called Co-teaching+, which bridges the "Update by Disagreement" strategy with the original Co-teaching. First, two networks feed forward and predict all data, but keep prediction disagreement data only. Then, among such disagreement data, each network selects its small-loss data, but back propagates the small-loss data from its peer network and updates its own parameters. Empirical results on benchmark datasets demonstrate that Co-teaching+ is much superior to many state-of-the-art methods in the robustness of trained models.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Learning with noisy labels | CIFAR-100N | Co-Teaching+ | Accuracy (mean) | 57.88 | #14 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Aggregate | Co-Teaching+ | Accuracy (mean) | 90.61 | #20 of 26 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random1 | Co-Teaching+ | Accuracy (mean) | 89.70 | #16 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random2 | Co-Teaching+ | Accuracy (mean) | 89.47 | #15 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random3 | Co-Teaching+ | Accuracy (mean) | 89.54 | #16 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Worst | Co-Teaching+ | Accuracy (mean) | 83.26 | #15 of 25 | 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