AI Paper Atlas

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

On Mixup Regularization

Luigi Carratino, Moustapha Cissé, Rodolphe Jenatton, Jean-Philippe Vert

JMLR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 83 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
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet standard (alpha=0.5)ECE: 0.0707 -> 0.0280Improved
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet standard (alpha=0.5)test CE-loss: 0.9482 -> 0.8852Improved
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet standard (alpha=0.25)accuracy: 0.7754 -> 0.7764Improved
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet standard (alpha=0.25)ECE: 0.0236 -> 0.0291Hurt
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet-A (alpha=0.5)ECE: 0.3161 -> 0.4318Hurt
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet-C (alpha=0.5)accuracy: 0.4761 -> 0.4719Hurt
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ImageNet-V2 (alpha=0.5)accuracy: 0.6575 -> 0.6593Improved
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · ObjectNet (alpha=0.5)accuracy: 0.2825 -> 0.2837Improved
apply the derived test-time rescaling to Mixup-trained models (ablation)Mixup (ResNet-50, ImageNet) · CIFAR-10-C and CIFAR-100-Caccuracy, CE-loss, ECE: gap grows in favor of standard Mixup as noise intensity growsHurt
apply the Mixup data transformation to an ERM-trained model (ablation)Mixup (ResNet-50, ImageNet) · CIFAR-10, CIFAR-100, ImageNetaccuracy, loss, ECE: performance always deterioratesHurt
apply the test-time transformation to Mixup with larger alpha (ablation)Mixup (ResNet-50, ImageNet) · CIFAR-10, CIFAR-100, ImageNetaccuracy, loss, ECE: bigger improvements for bigger alphaImproved

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