AI Paper Atlas

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

HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness

Mehmet Kerim Yucel, Ramazan Gokberk Cinbis, Pinar Duygulu

ICCV 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 21 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 HybridAugment++ (phase/amplitude swap on low-frequency component) on top of paired and single-image augmentation (ablation)HybridAugment · CIFAR-10-C (mean over 5 architectures)mCE: 9.2 -> 8.9Improved
lift same-class restriction in hybrid image sampling versus RFC (paired-only) (ablation)HybridAugment · CIFAR-10-C (mean over 5 architectures)mCE: 20.3 -> 14.5Improved
add HybridAugment++ to ResNet50 on ImageNetResNet50 · ImageNet-CmCE: 80.6 -> 67.3Improved
combine HA++_PS with DeepAugment and AugMixHybridAugment++ · ImageNet-CmCE: 62.0 -> 56.4Improved
use higher cut-off frequency (stronger blur) in HA++_PS on ImageNet (ablation)HybridAugment++ · ImageNet-CmCE: 67.3 -> 65.8 (clean error 23.7 -> 25.5)Mixed
use higher cut-off frequency on ImageNet-C-bar (ablation)HybridAugment++ · ImageNet-C-barerror: 52.2 -> 53.4Hurt
use kernel size K=3 with sigma 0.5 in Gaussian low-passHybridAugment++ · CIFAR-10/100 (ResNet18)clean accuracy and mCEImproved
use high-frequency image labels instead of low-frequency image labelsHybridAugment · CIFARoverall performanceHurt
add HybridAugment++ to adversarial training on CIFAR-10FGSM adversarial training · CIFAR-10 AutoAttackrobust accuracy: 43.2 -> 46.0Improved
add HA++_PS to adversarial training versus HA_SHybridAugment++ · CIFAR-10 AutoAttackclean accuracy: 86.5 -> 82.8Hurt
train with HybridAugment variants for OOD detectionResNet18 (CIFAR-10) · OOD detection (mean AUROC)AUROC: 88.1 -> 94.7Improved
paired-only HybridAugment variants on OOD detectionHybridAugment · OOD detection (mean AUROC)AUROC: 88.1 -> 89.0No 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