AI Paper Atlas

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

Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation

I-Hsiang Chen, Hua-En Chang, Wei-Ting Chen, Jenq-Neng Hwang, Sy-Yen Kuo

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 3 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 PDAF to DeepLabV3Plus ResNet-50DeepLabV3Plus · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 40.62 -> 49.41Improved
add PDAF to Mask2Former Swin-LMask2Former · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 58.13 -> 61.08Improved
add PDAF to Mask2Former Swin-T on ACDCMask2Former · ACDC (Cityscapes-trained)mIoU (avg over unseen domains): 53.15 -> 62.97Improved
add the Latent Prior Extractor (variational posterior) (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 45.19 -> 49.41Improved
add the Domain Compensation Module (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 47.82 -> 49.41Improved
add the Diffusion Prior Estimator (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 47.64 -> 49.41Improved
add semantic consistency loss on top of task loss (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 45.83 -> 46.80Improved
add prior constraint loss on top of task loss (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 45.83 -> 48.82Improved
add semantic consistency loss to task + prior loss (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 48.82 -> 49.41Improved
increase LDP channels from 4 to 1024 (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 49.41 -> 45.69Hurt
reduce LDP channels from 4 to 1 (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 49.41 -> 48.74Hurt
increase DPE diffusion steps from 4 to 32 (ablation)PDAF · Cityscapes-trained, unseen B/M/G/SmIoU (avg over unseen domains): 49.41 -> 49.48No clear effect

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