AI Paper Atlas

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

Exploring Weather-aware Aggregation and Adaptation for Semantic Segmentation under Adverse Conditions

Yuwen Pan, Rui Sun, Wangkai Li, Tianzhu Zhang

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 5 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 amplitude characteristic extraction, prompt aggregation, modulation and homogenization attention (ablation)WA2Net baseline · ACDCmIoU: 68.6 -> 73.8Improved
add amplitude characteristic extraction, prompt aggregation, modulation and homogenization attention (ablation)WA2Net baseline · NightCitymIoU: 52.4 -> 56.5Improved
add prompt aggregation (ablation)WA2Net · ACDCmIoU: 71.2 -> 73.8Improved
add prompt aggregation (ablation)WA2Net · NightCitymIoU: 54.9 -> 56.5Improved
add prompt aggregation and prompt-guided modulation (ablation)WA2Net · ACDCmIoU: 70.7 -> 73.8Improved
add prompt aggregation and prompt-guided modulation (ablation)WA2Net · NightCitymIoU: 53.7 -> 56.5Improved
replace cross-attention with homogenization attention (ablation)WA2Net · ACDCmIoU: 70.9 -> 73.8Improved
replace masked attention with homogenization attention (ablation)WA2Net · ACDCmIoU: 71.8 -> 73.8Improved
replace cross-attention with homogenization attention (ablation)WA2Net · NightCitymIoU: 54.1 -> 56.5Improved
replace masked attention with homogenization attention (ablation)WA2Net · NightCitymIoU: 55.0 -> 56.5Improved
add diversity loss on prompt bank (ablation)WA2Net · ACDCmIoU: 72.4 -> 73.8Improved
add diversity loss on prompt bank (ablation)WA2Net · NightCitymIoU: 56.0 -> 56.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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