Papers › Does label smoothing mitigate label noise?
Does label smoothing mitigate label noise?
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In this paper, we study whether label smoothing is also effective as a means of coping with label noise. While label smoothing apparently amplifies this problem --- being equivalent to injecting symmetric noise to the labels --- we show how it relates to a general family of loss-correction techniques from the label noise literature. Building on this connection, we show that label smoothing is competitive with loss-correction under label noise. Further, we show that when distilling models from noisy data, label smoothing of the teacher is beneficial; this is in contrast to recent findings for noise-free problems, and sheds further light on settings where label smoothing is beneficial.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | Positive-LS | Accuracy (mean) | 55.84 | #21 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Aggregate | Positive-LS | Accuracy (mean) | 91.57 | #15 of 26 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random1 | Positive-LS | Accuracy (mean) | 89.80 | #15 of 24 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random2 | Positive-LS | Accuracy (mean) | 89.35 | #16 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Random3 | Positive-LS | Accuracy (mean) | 89.82 | #13 of 23 | Archive leaderboard | report |
| Learning with noisy labels | CIFAR-10N-Worst | Positive-LS | Accuracy (mean) | 82.76 | #17 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.
Methods
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