AI Paper Atlas

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

FrequencyLowCut Pooling – Plug & Play against Catastrophic Overfitting

Julia Grabinski, Steffen Jung, Janis Keuper, Margret Keuper

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization

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 strided/standard pooling with FLC pooling in FGSM ATPRN-18 · CIFAR-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 0.00 -> 36.69Improved
replace pooling with FLC pooling in FGSM ATWRN-28-10 · CIFAR-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 0.09 -> 38.37Improved
replace pooling with FLC pooling in FGSM ATPRN-18 · CINIC-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 0.12 -> 49.61Improved
replace pooling with FLC pooling in FGSM ATPRN-18 · CIFAR-100 (FGSM AT)AutoAttack Linf 8/255 accuracy: 11.13 -> 15.40Improved
use BlurPooling instead of baseline pooling in FGSM ATPRN-18 · CIFAR-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 0.00 -> 0.06No clear effect
use Wavelet Pooling instead of baseline pooling in FGSM ATPRN-18 · CIFAR-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 0.00 -> 5.92No clear effect
add FLC pooling in clean trainingPRN-18 · CIFAR-10 (clean training)PGD L2 0.5 accuracy: 6.68 -> 11.27Improved
add FLC pooling in clean trainingPRN-18 · CIFAR-10 (clean training)clean accuracy: 95.08 -> 94.66Hurt
add FLC pooling to FGSM AT versus FGSM with early stoppingPRN-18 · CIFAR-10 (FGSM AT)AutoAttack Linf 8/255 accuracy: 3.76 -> 36.69Improved
add FLC pooling instead of BlurPooling for shift consistencyPRN-18 · CIFAR-10 (shift)consistency under shift: 86.19 -> 94.46Improved
add high-frequency path to FLC pooling (ablation)FLC pooling · CIFAR-10 (FGSM AT)PGD Linf 8/255 accuracy: 38.41 -> 38.02No clear effect
add original-path pooling to FLC pooling (ablation)FLC pooling · CIFAR-10 (FGSM AT)PGD Linf 8/255 accuracy: 38.41 -> 38.30No clear effect

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