Research map / Label-efficient and robust learning / Domain adaptation and generalization
ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation
Hanxiang Ren, Yanchao Yang, He Wang, Bokui Shen, Qingnan Fan, Youyi Zheng, C. Karen Liu, Leonidas J. Guibas
Check 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 attention-based spatial transportation instead of UNet color transformation for label hallucination (ablation) | ADeLA · Target domains 10°–90° | mIoU of hallucinated labels | Improved |
| Add functional label hallucination instead of nearest-neighbor conversion (ablation) | ADeLA (single) · Target domains 10°–90° | mIoU of hallucinated labels: 54.85 -> 70.07; 46.29 -> 67.63; 42.66 -> 58.62; 37.75 -> 54.33; 27.71 -> 47.45; 21.33 -> 37.81; 14.18 -> 28.39; 8.69 -> | Improved |
| Use single-target rather than multiple-target view hallucination (ablation) | ADeLA · Target domains 10°–70° | mIoU of hallucinated labels: 48.42 -> 54.85; 41.87 -> 46.29; 35.73 -> 42.66; 30.39 -> 37.75; 24.11 -> 27.71; 17.40 -> 21.33; 11.79 -> 14.18 | Improved |
| Use multiple-target rather than single-target view hallucination (ablation) | ADeLA · 80° and 90° target domains | mIoU of hallucinated labels: 8.69 -> 8.82; 4.17 -> 7.34 | Mixed |
| Use learned flow-based 2D correspondence rather than UNet transformation (ablation) | View hallucination · Large viewpoint changes | mIoU of hallucinated labels | Improved |
| Use learned flow-based correspondence rather than fully supervised RAFT correspondence (ablation) | View hallucination · Small viewpoint changes | mIoU of hallucinated labels | Hurt |
| Use fully supervised RAFT correspondence rather than learned Flow (ablation) | View hallucination · Large viewpoint changes | mIoU of hallucinated labels | Hurt |
| Use 3D view synthesis rather than UNet transformation (ablation) | View hallucination · Target domains | mIoU of hallucinated labels | Hurt |
| Add functional label hallucination (ablation) | UNet · Target domains 10°–90° | mIoU of hallucinated labels: 49.76 -> 73.62; 28.19 -> 49.07; 13.69 -> 27.12; 9.26 -> 20.08; 6.56 -> 16.48; 4.71 -> 13.68; 2.59 -> 11.61; 1.63 -> 9.79 | Improved |
| Use ADeLA instead of the strongest listed baseline | Semantic segmentation adaptation · 10° target domain test | mIoU: 37.80 -> 31.19 | Hurt |
| Use ADeLA instead of the strongest listed baseline | Semantic segmentation adaptation · 20°–90° target domain tests | mIoU: 26.74 -> 27.66; 24.15 -> 24.31; 17.75 -> 20.71; 8.66 -> 15.88; 5.68 -> 12.28; 4.67 -> 8.27; 3.87 -> 7.16; 3.39 -> 5.03 | Improved |
Closest papers by meaning
- ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation (CVPR 2020 · similarity 0.89)
- Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation (ECCV 2020 · similarity 0.88)
- D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation (ECCV 2022 · similarity 0.88)
- Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation (CVPR 2021 · similarity 0.87)
- CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation (ICCV 2023 · similarity 0.87)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · 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.
