Research map / Label-efficient and robust learning / Domain adaptation and generalization
Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation
Yuxi Wang, Jian Liang, Jun Xiao, Shuqi Mei, Yuran Yang, Zhaoxiang 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 sample-selected minimization (SSM) (ablation) | DAFormer one-shot · GTA5->Cityscapes one-shot | mIoU: 50.6 -> 52.0 | Improved |
| add prototype-based information maximization (PIM) to SSM (ablation) | IDM · GTA5->Cityscapes one-shot | mIoU: 52.0 -> 53.2 | Improved |
| add PatchMix to SSM (ablation) | IDM · GTA5->Cityscapes one-shot | mIoU: 52.0 -> 55.0 | Improved |
| use PatchMix instead of ClassMix (ablation) | IDM · GTA5->Cityscapes one-shot | mIoU: 55.9 -> 56.7 | Improved |
| add SSM when PatchMix and PIM present (ablation) | IDM · GTA5->Cityscapes one-shot | mIoU: 54.8 -> 56.7 | Improved |
| add style transfer plus prediction and similarity uncertainty selection (ablation) | IDM sample selection · GTA5->Cityscapes one-shot | iterations to reach mIoU: 20000 -> 300 iterations, 50.6 -> 52.0 mIoU | Improved |
| naively reduce target data of UDA method to one shot | DAFormer · GTA5->Cityscapes | mIoU: 68.3 -> 50.6 | Hurt |
| vary thresholds lambda_ent, lambda_sim, k (ablation) | IDM · GTA5->Cityscapes | mIoU: 50.8 - 51.4 (lambda_ent) | No clear effect |
| apply IDM to DeepLab-v2 backbone (ablation) | DeepLab-v2 · GTA5->Cityscapes one-shot | mIoU: 41.1 -> 45.2 | Improved |
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
- Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation (NeurIPS 2022 · similarity 0.90)
- Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation (NeurIPS 2021 · similarity 0.90)
- Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision (CVPR 2020 · similarity 0.90)
- Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation (AAAI 2022 · similarity 0.90)
- Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation (ICML 2025 · similarity 0.89)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.88)
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.
