Research map / Label-efficient and robust learning / Domain adaptation and generalization
VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
Mingjia Li, Binhui Xie, Shuang Li, Chi Harold Liu, Xinjing Cheng
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 |
|---|---|---|---|
| Use VBLC instead of FDA | DeepLab-v2 · ACDC test | mIoU: 45.7 -> 47.8; +2.1% | Improved |
| Use VBLC instead of DAFormer | SegFormer · ACDC test | mIoU: 55.3 -> 64.2; +8.9% | Improved |
| Use VBLC instead of DAFormer | SegFormer · FoggyCityscapes + RainCityscapes | mIoU: 74.9 -> 79.8 | Improved |
| Add VBLC modules to SFA | Deformable DETR detection · FoggyCityscapes + RainCityscapes | AP: 14.3 -> 15.6; 1.3 AP | Improved |
| Add conventional cross-entropy self-training on source-target blended images (ablation) | SegFormer · Cityscapes → ACDC | mIoU: 45.9 -> 52.6; +6.7% | Improved |
| Add visibility boosting and boosted-image cross-entropy supervision (ablation) | SegFormer with self-training · Cityscapes → ACDC | mIoU: 52.6 -> 57.0; 4.4↑ | Improved |
| Use target logit-constraint learning instead of target cross-entropy losses (ablation) | VBM + self-training · Cityscapes → ACDC | mIoU: 57.0 -> 63.2; +6.2% | Improved |
| Add source-domain logit-constraint learning (ablation) | VBM + target logit-constraint learning · Cityscapes → ACDC | mIoU: 63.2 -> 64.2; +1.0% | Improved |
Later papers that compared with this method
1 later accepted paper reports VBLC as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions (CVPR 2026 · better on 1 of 1 shared result)
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.
- DAFormer — DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation (CVPR 2022) · better on 2 of 2 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
- Exploring Weather-aware Aggregation and Adaptation for Semantic Segmentation under Adverse Conditions (ICCV 2025 · similarity 0.88)
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (AAAI 2024 · similarity 0.87)
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency (AAAI 2024 · similarity 0.87)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.86)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.85)
- Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation (NeurIPS 2025 · similarity 0.85)
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.
