AI Paper Atlas

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

Causal Inference via Style Bias Deconfounding for Domain Generalization

Jiaxi Li, Di Lin, Hao Chen, Hongying Liu, Liang Wan, Wei Feng

TPAMI 2026 · 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 SDCL (style deconfounding causal learning) to SHADESHADE · Digits single-domain (train MNIST)accuracy (%): 81.20 -> 82.07Improved
add SDCL (style deconfounding causal learning) to AdvSTAdvST · PACS single-domainavg accuracy (%): 68.07 -> 71.00Improved
add SDCL (style deconfounding causal learning) to SHADESHADE · PACS single-domainavg accuracy (%): 68.47 -> 70.40Improved
add SDCL (style deconfounding causal learning) to SHADESHADE · PACS multi-domain (leave-one-out)avg accuracy (%): 85.31 -> 86.95Improved
add SDCL (style deconfounding causal learning) to TLDRTLDR · GTAV to real (single-domain)avg mIoU (%): 47.00 -> 48.47Improved
add SDCL (style deconfounding causal learning) to TLDRTLDR · GTAV+SYNTHIA to real (multi-domain)avg mIoU (%): 42.38 -> 44.40Improved
add SDCL (style deconfounding causal learning) to SHADESHADE · GTAV+SYNTHIA to real (multi-domain)avg mIoU (%): 45.11 -> 46.90Improved
add SDCL (style deconfounding causal learning) to SLAugSLAug · CDCS cardiac multi-domain (leave-one-out)avg Dice (%): 84.80 -> 86.45Improved
add BDCL (back-door causal learning) on top of SGEM (ablation)SDCL · PACS single-domainavg accuracy (%): 69.83 -> 71.00Improved
add BDCL on top of SGEM (ablation)SDCL · GTAV to real (single-domain)avg mIoU (%): 47.93 -> 48.47Improved
add SGEM (style-guided expert module) to the base augmentation method (ablation)UDP/AdvST/TLDR/SLAug · PACS single-domainavg accuracy (%): 68.07 -> 69.83Improved
place SGEM at ResNet layer 1 instead of layer 4 (ablation)SDCL · PACS single-domainaccuracy (%): 67.12 -> 71.00Improved

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