AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Geometric and Textural Augmentation for Domain Gap Reduction

Xiao-Chang Liu, Yong-Liang Yang, Peter Hall

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 16 citations (OpenAlex)

Check 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 geometric and texture augmentation (ablation)ResNet-18 · PACS multi-sourceaccuracy: 79.51 -> 86.56Improved
Add texture augmentation (ablation)ResNet-18 with geometric augmentation · PACS multi-sourceaccuracy: 83.05 -> 86.56Improved
Add geometric augmentation (ablation)ResNet-18 with texture augmentation · PACS multi-sourceaccuracy: 86.07 -> 86.56Improved
Add geometric and texture augmentation (ablation)ResNet-50 · PACS multi-sourceaccuracy: 82.02 -> 89.17Improved
Add geometric and texture augmentation (ablation)the proposed method · Office-Home multi-sourceaccuracy: 64.01 -> 66.75Improved
Add geometric augmentation (ablation)the proposed method with texture augmentation · Office-Home multi-sourceaccuracy: 65.12 -> 66.75Improved
Add texture augmentation (ablation)the proposed method with geometric augmentation · Office-Home multi-sourceaccuracy: 66.60 -> 66.75Improved
Add geometric and texture augmentation (ablation)the proposed method · Digits-DG multi-sourceaccuracy: 75.0 -> 82.6Improved
Add geometric augmentation (ablation)the proposed method with texture augmentation · Digits-DG multi-sourceaccuracy: 78.6 -> 82.6Improved
Add texture augmentation (ablation)the proposed method with geometric augmentation · Digits-DG multi-sourceaccuracy: 80.3 -> 82.6Improved
Use geometric and texture augmentationthe proposed method · PACS single-sourceaccuracy: +3%Improved
Use geometric and texture augmentationthe proposed method · PACS multi-sourceaccuracy: 86.56 vs 84.51Improved

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