AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition

Xilin He, Qinliang Lin, Cheng Luo, Weicheng Xie, Siyang Song, Feng Liu, Linlin Shen

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 6 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 all three modules (EMSE, TSD, TSG) to the Canny+Pix2Pix baseline (ablation)SDbOA · CIFAR-10 PGDrobust accuracy (%): 46.78 -> 50.91Improved
add all three modules to the baseline (ablation)SDbOA · CIFAR-10 C&Wrobust accuracy (%): 45.48 -> 56.06Improved
add all three modules to the baseline (ablation)SDbOA · CIFAR-10clean accuracy (%): 74.32 -> 83.27Improved
increase TPS deformation intensity lambda beyond 0.1 (ablation)SDbOA · shape-bias metricssbGE and sbISHurt
use SDbOA augmentation instead of standard training on ImageNetResNet-50 · ImageNet cue-conflictsbGE (%): 21.39 -> 71.28Improved
use SDbOA instead of PixMix on common corruptionsWideResNet-40-4 · CIFAR-10-CmCE (%): 9.5 vs 18.8Hurt
use SDbOA instead of AugMax on adversarial errorWideResNet-40-4 · CIFAR-10 PGD-20misclassification rate (%): 39.1 -> 27.7Improved
use SDbOA instead of generative adversarial training (FDA, PORT) with lower runtimeWideResNet-34-10 · CIFAR-10 AutoAttackrobust accuracy (%): 60.60 -> 73.36Improved
use SDbOA on clean data instead of vanilla trainingResNet18 · CIFAR-10clean accuracy (%): 90.70 -> 83.27Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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