AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Understanding the Generalization Benefit of Model Invariance from a Data Perspective

Sicheng Zhu, Bang An, Furong Huang

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Statistical perspectives on generalization · 3 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
add cropping invariance via augmentationResNet18 · CIFAR-10 n=100test accuracy (%): 41.05 -> 50.47Improved
add flip invariance via augmentationResNet18 · CIFAR-10 n=100test accuracy (%): 41.05 -> 44.19Improved
add rotation invariance via augmentationResNet18 · CIFAR-10 n=100test accuracy (%): 41.05 -> 47.02Improved
add cropping invariance via augmentation, full dataResNet18 · CIFAR-10 n=allgeneralization gap: 14.57 -> 7.48Improved
add 3D-view invariance via augmentationResNet18 · ShapeNet n=100test accuracy (%): 67.75 -> 78.13Improved
add 3D-view invariance via augmentationResNet18 · ShapeNet n=100generalization gap: 32.25 -> 14.94Improved
add cropping invariance via augmentationResNet18 · ShapeNet n=100test accuracy (%): 67.75 -> 74.88Improved
add 3D-view invariance via augmentation, full dataResNet18 · ShapeNet n=alltest accuracy (%): 91.81 -> 94.38Improved
add flip invariance via augmentation, full dataResNet18 · ShapeNet n=alltest accuracy (%): 91.81 -> 92.07No clear effect
add rotation invariance via augmentation, full dataResNet18 · ShapeNet n=alltest accuracy (%): 91.81 -> 91.85No clear effect
increase invariance penalty lambda from 0 to 1 (ablation)ResNet18, 3D-view regularization · ShapeNettest accuracy (%): 91.81 -> 94.68Improved
increase invariance penalty lambda from 0 to 100 (ablation)ResNet18, 3D-view regularization · ShapeNetgeneralization gap: 8.19 -> 1.03Improved

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