AI Paper Atlas

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

Group-Wise Inhibition Based Feature Regularization for Robust Classification

Haozhe Liu, Haoqian Wu, Weicheng Xie, Feng Liu, Linlin Shen

ICCV 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization · 16 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 channel-wise inhibition to the baseline (ablation)ResNet-18 · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 77.1 -> 81.2Improved
use group-wise inhibition (CFG + GMW) instead of baseline (ablation)ResNet-18 · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 77.1 -> 81.8Improved
add orthogonal loss L_o to group-wise inhibition (ablation)TENET · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 81.8 -> 82.3Improved
replace binary mask with smoothed reversed maps (RRF) (ablation)TENET · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 81.1 -> 82.3Improved
replace instance-wise Grad-CAM inhibition with group-wise CFG/GMW (ablation)TENET · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 81.3 -> 82.3Improved
add TENET regularization (vs GoCNN, no annotations)ResNet-18 · PASCAL VOC 2012 val (ImageNet-pretrained)mean AP: 79.4 -> 82.3Improved
combine TENET with AugmixResNet-50 · ImageNet-C (90-epoch protocol)mCE: 75.3 -> 71.1Improved
TENET (Aug.) vs AugmixResNet-50 · ImageNet-C (180-epoch protocol)mCE: 70.5 -> 69.6Improved
add TENET to AugmixResNeXt-29 · CIFAR-10-CmCE: 13.32 -> 12.31Improved
add TENET to AugmixResNeXt-29 · CIFAR-10 FGSM (8/255)top-1 error: 76.03 -> 60.47Improved
add TENET to adversarial trainingResNeXt-29 · CIFAR-10 FGSM (8/255)top-1 error: 36.37 -> 31.75Improved
add TENET to adversarial trainingResNeXt-29 · CIFAR-100 PGD-100 (8/255)top-1 error: 65.17 -> 63.13Improved

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