AI Paper Atlas

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

Split-and-Combine: Enhancing Style Augmentation for Single Domain Generalization

Zhen Zhang, Shuai Yang, Qianlong Dang, Zhize Wu, Lichuan Gu

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 2 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 ARC (adaptive random convolution) (ablation)SAC · Digitsaverage accuracy: 77.7 -> 88.3Improved
add PAA (ablation)SAC · Digitsaverage accuracy: 85.3 -> 88.3Improved
add Gaussian filter g (ablation)SAC · Digitsaverage accuracy: 86.8 -> 88.3Improved
add feature-level discrepancy loss Ld (ablation)SAC · Digitsaverage accuracy: 87.4 -> 88.3Improved
add pixel-level discrepancy loss Lp (ablation)SAC · Digitsaverage accuracy: 87.0 -> 88.3Improved
use adaptive iteration strategy (Eq. 9) instead of random T in U[1,10] (ablation)SAC · Digitsaverage accuracy: 86.9 -> 88.3Improved
use adaptive strategy instead of fixed T=10 (ablation)SAC · Digitsaverage accuracy: 86.1 -> 88.3Improved
apply SAC to PDENPDEN · Digitsaverage accuracy: 74.8 -> 83.0Improved
apply SAC to L2DL2D · Digitsaverage accuracy: 74.5 -> 76.4Improved
apply SAC to PSDGPSDG · Digitsaverage accuracy: 84.7 -> 87.0Improved
apply ARC to Pro-RandConvPro-RandConv · Digitsaverage accuracy: 81.4 -> 83.6Improved
use deformable convolution instead of conventional convolution (ablation)SAC · Digitsaverage accuracy: 86.4 -> 88.3Improved

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