AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

Jungmin Kwon, Jeongseop Kim, Hyunseo Park, In Kwon Choi

ICML 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace SAM's fixed-radius perturbation with scale-adaptive perturbations (ASAM)PyramidNet-272 · CIFAR-10test accuracy: 98.55_{\pm 0.05} -> 98.68_{\pm 0.08}Improved
Replace SAM's fixed-radius perturbation with scale-adaptive perturbations (ASAM)PyramidNet-272 · CIFAR-100test accuracy: 89.36_{\pm 0.20} -> 89.90_{\pm 0.13}Improved
Replace SAM with ASAMResNet-50 · ImageNetTop1 accuracy: 76.39_{\pm 0.03} -> 76.63_{\pm 0.18}Improved
Replace Adam+SAM with Adam+ASAMTransformer · IWSLT'14 DE-EN testBLEU: 34.78_{\pm 0.01} -> 35.02_{\pm <0.01}Improved
Replace SAM with ASAMResNet-32 · CIFAR-10 with 20%, 40%, and 60% label noisetest accuracy: 92.94_{\pm 0.12} -> 93.21_{\pm 0.10}; 90.62_{\pm 0.18} -> 90.89_{\pm 0.13}; 86.58_{\pm 0.30} -> 87.41_{\pm 0.16}Improved
Replace SAM with ASAMResNet-32 · CIFAR-10 with 80% label noisetest accuracy: 69.92_{\pm 0.98} -> 67.69_{\pm 1.34}Hurt
Use p=2 rather than p=∞ for the adaptive maximization region (ablation)ASAM · CIFAR image classificationtest accuracyImproved
Add bias normalization (ablation)ASAM with element-wise normalization and p=2 · CIFAR image classificationtest accuracyNo clear effect
Use element-wise rather than filter-wise normalization (ablation)ASAM with WideResNet-16-8 · CIFAR image classificationtest accuracyNo clear effect
Use adaptive sharpness rather than ordinary sharpness (ablation)Generalization-gap measure · WideResNet-28-2 on CIFAR-10Kendall rank correlation τ: 0.174 -> 0.636 (p=2); 0.257 -> 0.616 (p=∞)Improved

Later papers that compared with this method

3 later accepted papers report ASAM as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy