AI Paper Atlas

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

ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving

Dingyi Yao, Xinqi Zhang, Lihui Peng, Jianming HU, Danya Yao, Yi ZHANG

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 0 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 semantically constrained adaptive attention filtering (ablation)ASTModel · structural fidelityLPIPS: 0.5114 -> 0.3588Improved
add pixel-proportion modulated hybrid AdaIN (vs global AdaIN) (ablation)ASTModel · structural fidelityLPIPS: 0.3737 -> 0.3588Improved
add multi-layer semantic voting (ablation)ASTModel · structural fidelityLPIPS: 0.3641 -> 0.3588Improved
refine style prior with multi-layer voting (Stage-II) (ablation)ASTModel pseudo labels · style-side pseudo labelsPixel Acc: 0.688 -> 0.790Improved
refine style prior with multi-layer voting (Stage-II) (ablation)ASTModel pseudo labels · style-side pseudo labelsmIoU: 0.281 -> 0.339Improved
use Median/MAD instead of Mean/Std for filtering threshold (ablation)ASTModel attention filtering · attention entries retainedfraction kept (%): 1.8% -> 33.2%Improved
use ASTModel instead of CACTIF for synthetic-to-real transferdownstream SegFormer · GTA to real downstream segmentationmIoU: 0.289 -> 0.309Improved
use ASTModel instead of source-only trainingdownstream SegFormer · GTA to real downstream segmentationPixel Acc: 0.844 -> 0.847No clear effect
use ASTModel instead of CACTIFstyle transfer · inference time per imageseconds: 80s -> 25sImproved
use ASTModel instead of Cross-Image Attentionstyle transfer · inference time per imageseconds: 18s -> 25sHurt

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