AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt and 1 more

ICCV 2021 · Label-efficient and robust learning › OOD and anomaly detection · approach: Robust fine-tuning for OOD generalization · 1,472 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 DeepAugment + AugMix augmentation (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 53.2Improved
add DeepAugment augmentation (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 57.8Improved
add ImageNet-21K pretraining (10x labeled data) (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 62.8No clear effect
add CBAM self-attention (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 63.2No clear effect
add l_inf adversarial training (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 68.6Hurt
add speckle noise augmentation instead of diverse augmentation (ablation)ResNet-50 · ImageNet-Rtop-1 error (%): 63.9 -> 62.1No clear effect
scale model from ResNet-50 to ResNet-152 (ablation)ResNet · ImageNet-Rtop-1 error (%): 63.9 -> 58.7Improved
add WSL pretraining on 1B Instagram images (ablation)ResNeXt-101 32x8d · ImageNet-Rtop-1 error (%): 57.5 -> 24.2Improved
add DeepAugment + AugMix augmentation (ablation)ResNet-50 · ImageNet-CmCE: 76.7 -> 53.6Improved
add DeepAugment + AugMix augmentation (ablation)ResNeXt-101 32x8d · ImageNet-CmCE: 66.7 -> 44.5Improved
add DeepAugment + AugMix augmentation (ablation)ResNet-50 · Real Blurry Imagestop-1 error (%): 58.7 -> 51.7Improved
add data augmentation (Style Transfer, DeepAugment, AugMix) (ablation)ResNet-50 · SVSF (France)classification error (%): 56.7 -> 59.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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