Research map / Detection and segmentation / Open-set and few-shot detection
Exploit Domain-Robust Optical Flow in Domain Adaptive Video Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SFC supervision based on optical-flow consistency | Accel · VIPER → Cityscapes-Seq | mIoU: 46.58 -> 48.02 | Helped |
| Use SFC supervision based on optical-flow consistency | Accel · SYNTHIA-Seq → Cityscapes-Seq | mIoU: 54.0 -> 55.3 | Helped |
| Add temporal pseudo labeling (ablation) | SFC on Accel · VIPER → Cityscapes-Seq | mIoU: 51.1 -> 51.7 | Helped |
| Add temporal pseudo labeling (ablation) | SFC on Accel · SYNTHIA-Seq → Cityscapes-Seq | mIoU: 52.5 -> 55.3 | Helped |
| Add SFC (ablation) | DFF · VIPER → Cityscapes-Seq | mIoU: 37.04 -> 48.51 | Helped |
| Add SFC (ablation) | DA-VSS · VIPER → Cityscapes-Seq | mIoU: 38.70 -> 48.97 | Helped |
| Replace FlowNet with RAFT for flow estimation (ablation) | SFC · VIPER → Cityscapes-Seq | mIoU: 38.64 -> 51.57 | Helped |
| Use source-only training instead of SFC (ablation) | Accel with FlowNet · VIPER → Cityscapes-Seq | mIoU: 51.05 -> 37.39 | Hurt |
| Use SFC supervision in stage one (ablation) | Accel · VIPER → Cityscapes-Seq | mIoU: 46.71 -> 48.87 | Helped |
| Use SFC supervision in stage two (ablation) | Accel · VIPER → Cityscapes-Seq | mIoU: 46.58 -> 48.02 | Helped |
| Train on source domain rather than target domain | SegNet · Cityscapes-Seq and VIPER domain analysis | mIoU: 70.39 -> 45.76; 67.38 -> 47.07 | Hurt |
| Train on source domain rather than target domain | FlowNet · Cityscapes-Seq and VIPER domain analysis | mIoU: 67.96 -> 65.25; 62.47 -> 63.84 | No clear effect |
Closest papers by meaning
- Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow (AAAI 2020 · similarity 0.90)
- Pay Attention to Target: Relation-Aware Temporal Consistency for Domain Adaptive Video Semantic Segmentation (AAAI 2024 · similarity 0.89)
- On the Road to Online Adaptation for Semantic Image Segmentation (CVPR 2022 · similarity 0.88)
- FDA: Fourier Domain Adaptation for Semantic Segmentation (CVPR 2020 · similarity 0.88)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation (NeurIPS 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.