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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add amplitude characteristic extraction, prompt aggregation, modulation and homogenization attention (ablation) | WA2Net baseline · ACDC | mIoU: 68.6 -> 73.8 | Improved |
| add amplitude characteristic extraction, prompt aggregation, modulation and homogenization attention (ablation) | WA2Net baseline · NightCity | mIoU: 52.4 -> 56.5 | Improved |
| add prompt aggregation (ablation) | WA2Net · ACDC | mIoU: 71.2 -> 73.8 | Improved |
| add prompt aggregation (ablation) | WA2Net · NightCity | mIoU: 54.9 -> 56.5 | Improved |
| add prompt aggregation and prompt-guided modulation (ablation) | WA2Net · ACDC | mIoU: 70.7 -> 73.8 | Improved |
| add prompt aggregation and prompt-guided modulation (ablation) | WA2Net · NightCity | mIoU: 53.7 -> 56.5 | Improved |
| replace cross-attention with homogenization attention (ablation) | WA2Net · ACDC | mIoU: 70.9 -> 73.8 | Improved |
| replace masked attention with homogenization attention (ablation) | WA2Net · ACDC | mIoU: 71.8 -> 73.8 | Improved |
| replace cross-attention with homogenization attention (ablation) | WA2Net · NightCity | mIoU: 54.1 -> 56.5 | Improved |
| replace masked attention with homogenization attention (ablation) | WA2Net · NightCity | mIoU: 55.0 -> 56.5 | Improved |
| add diversity loss on prompt bank (ablation) | WA2Net · ACDC | mIoU: 72.4 -> 73.8 | Improved |
| add diversity loss on prompt bank (ablation) | WA2Net · NightCity | mIoU: 56.0 -> 56.5 | Improved |
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.
- DAFormer — DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation (CVPR 2022) · better on 3 of 3 shared results
- HRDA — HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation (ECCV 2022) · better on 3 of 3 shared results
- CoDA — CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding (ICLR 2021) · better on 3 of 3 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
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (AAAI 2024 · similarity 0.93)
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency (AAAI 2024 · similarity 0.91)
- End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning (NeurIPS 2024 · similarity 0.91)
- UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather (CVPR 2024 · similarity 0.89)
- ERF: A Benchmark Dataset for Robust Semantic Segmentation Under Extreme Rainfall Conditions (AAAI 2025 · similarity 0.89)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.86)
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.
