Research map / Label-efficient and robust learning / Domain adaptation and generalization
Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
Shiqin Wang, Haoyang Chen, Huaizhou Huang, Yinkan He, Dongfang Sun, Xiaoqing Chen, Xingyu Liu, Zheng Wang, Kaiyan Zhao
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 low-dimensional state representation learning (LSRL) (ablation) | HeuSCM (HRDA, Refign baseline) · ACDC val | mIoU (%): 71.1 -> 72.2 | Improved |
| add SKFEN (ablation) | HeuSCM (HRDA) · ACDC val | mIoU (%): 71.1 -> 71.7 | Improved |
| add categorical alpha-fairness policy gradient (CaPG) (ablation) | HeuSCM (HRDA) · ACDC val | mIoU (%): 71.1 -> 71.6 | Improved |
| combine all three components (ablation) | HeuSCM (HRDA) · ACDC val | mIoU (%): 71.1 -> 72.7 | Improved |
| use HeuSCM instead of Refign | HRDA · ACDC test | mIoU (%): 72.1 -> 72.9 | Improved |
| use HeuSCM instead of CoDA | HRDA · ACDC test | mIoU (%): 72.6 -> 72.9 | No clear effect |
| use HeuSCM instead of ACSegFormer | HRDA · ACDC val | mIoU (%): 72.6 -> 72.7 | No clear effect |
| use HeuSCM instead of InforMS | HRDA · Dark Zurich val | mIoU (%): 52.5 -> 52.8 | No clear effect |
| replace sampling strategy with HCSP | IAST · GTA5->Cityscapes | mIoU (%): 52.2 -> 52.4 | No clear effect |
| replace sampling strategy with HCSP | HIAST · GTA5->Cityscapes | mIoU (%): 56.3 -> 56.5 | No clear effect |
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.
- HRDA — HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation (ECCV 2022) · better on 2 of 2 shared results
- CoDA — CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding (ICLR 2021) · better on 2 of 2 shared results
- VBLC — VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions (AAAI 2023) · better on 1 of 1 shared result
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
- Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach (ICCV 2019 · similarity 0.89)
- A Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation (TPAMI 2024 · similarity 0.89)
- A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes (TPAMI 2019 · similarity 0.89)
- Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation (IJCV 2024 · similarity 0.89)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.87)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.87)
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.
