AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise

Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Layer-wise analysis of language models

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
use patch size 32 instead of 16 (ablation)ViT-B augreg in1k 224 · ImageNet-1K Gaussian noiseRankDiff: -375 -> -506Improved
use native resolution 224 instead of 384 (pre-resize noise) (ablation)ViT-B/16 augreg in1k · ImageNet-1K Gaussian noiseRankDiff: -152 -> -375Improved
add noise after resizing instead of before (counterfactual) (ablation)supervised ViT pairs 224 vs 384 · consistency gap 384 minus 224mean consistency gap: -0.50 (34/63) -> +4.18 (62/63)Mixed
use average pooling in stem instead of max pooling (ablation)ResNet-50 · FGVC-Aircraft (noisy test)accuracy with noise: 27.3 -> 43.1Improved
use average pooling in stem instead of max pooling (ablation)ResNet-50 · Oxford-IIIT Pet (noisy test)accuracy with noise: 41.8 -> 49.3Improved
use average pooling in stem instead of max pooling (ablation)ResNet-50 · Caltech-UCSD Birds-200-2011 (noisy test)accuracy with noise: 26.1 -> 26.8No clear effect
use nearest-neighbor pooling instead of max pooling (ablation)ResNet-50 · FGVC-Aircraft (noisy test)accuracy with noise: 27.3 -> 24.7Hurt
use average-pooling downsampling (ResNet-T) instead of strided convolution (ResNet-S) (ablation)ResNet-50 · Oxford-IIIT Pet (noisy test)accuracy with noise: 22.9 -> 38.1Improved
replace OPENAI normalization constants with INCEPTION constants (ablation)CLIP ViT-B/16 openai ft in12k · Oxford-IIIT Pet (noisy test)accuracy with noise: 76.3 -> 87.2Improved
replace OPENAI normalization constants with IMAGENET constants (ablation)CLIP ViT-B/16 openai ft in12k · Oxford-IIIT Pet (noisy test)accuracy with noise: 76.3 -> 72.7Hurt
use INCEPTION constants instead of OPENAI (ablation)supervised ViT-B/16 augreg in1k · Oxford-IIIT Pet (noisy test)accuracy with noise: 88.2 -> 89.2No clear effect
use supervised ViT instead of CLIP ViTViT-B/16 224 · ImageNet-1K Gaussian noiseRankDiff: +74 -> -65Improved

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