AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 48 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 spectral transformation to PRIME (ablation)PRIME (ResNet-18) · ImageNet-100-C (no JSD)corruption accuracy: 49.7 -> 64.1Improved
add spatial transformation alone (ablation)PRIME (ResNet-18) · ImageNet-100-C (no JSD)corruption accuracy: 49.7 -> 53.8Improved
add color transformation alone (ablation)PRIME (ResNet-18) · ImageNet-100-C (no JSD)corruption accuracy: 49.7 -> 59.9Improved
add color to spectral+spatial (ablation)PRIME (ResNet-18) · ImageNet-100-C (no JSD)corruption accuracy: 64.5 -> 68.8Improved
add spatial to spectral+color (ablation)PRIME (ResNet-18) · ImageNet-100-C (no JSD)corruption accuracy: 67.5 -> 68.8Improved
add primitives (all three) on clean accuracy (ablation)PRIME (ResNet-18) · ImageNet-100 cleanaccuracy: 88.0 -> 87.1Hurt
add mixing of transformed images (ablation)PRIME · Min. cosine distance to ImageNet-C (SimCLRv2)min cosine distance (x1e-3), lower better: 10.61 -> 7.71Improved
add mixing to AugMix (ablation)AugMix · Min. cosine distance to ImageNet-C (SimCLRv2)min cosine distance (x1e-3), lower better: 20.57 -> 17.48Improved
replace AugMix primitives with PRIME max-entropy primitivesAugMix-style mixing · Min. cosine distance to ImageNet-C (SimCLRv2)min cosine distance (x1e-3), lower better: 17.48 -> 7.71Improved
replace AugMix with PRIMEResNet-18 · ImageNet-100-Ccorruption accuracy: 60.7 -> 71.6Improved
add PRIME on top of DeepAugmentResNet-18 · ImageNet-100-CmCE: 68.1 -> 54.6Improved
add BN-statistics adaptation with 8 corrupted samplesPRIME (ResNet-18) · ImageNet-100-Ccorruption accuracy: 71.6 -> 75.3Improved

Later papers that compared with this method

1 later accepted paper reports PRIME as a baseline in their results tables; 0 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