Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow
Hanyu Zhou, Yi Chang, Gang Chen, Luxin Yan
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 |
|---|---|---|---|
| Transfer clean-domain motion with hierarchical motion and boundary adaptation | Optical flow estimation under adverse weather · LR-KITTI | EPE: 6.98 -> 5.86 | Improved |
| Transfer clean-domain motion with hierarchical motion and boundary adaptation | Optical flow estimation under adverse weather · HR-KITTI | EPE: 6.95 -> 6.47 | Improved |
| Transfer clean-domain motion with hierarchical motion and boundary adaptation | Optical flow estimation under adverse weather · GOF Rain | EPE: 1.07 -> 0.91 | Improved |
| Transfer clean-domain motion with hierarchical motion and boundary adaptation | Optical flow estimation under adverse weather · GOF Fog | EPE: 0.95 -> 0.84 | Improved |
| Add flow consistency and feature alignment (ablation) | HMBA-FlowNet · LR-KITTI | EPE: 9.14 -> 6.65 | Improved |
| Add flow consistency and feature alignment (ablation) | HMBA-FlowNet · HR-KITTI | EPE: 10.61 -> 6.89 | Improved |
| Add intra- and inter-scene boundary contrastive losses (ablation) | HMBA-FlowNet with motion consistency adaptation · LR-KITTI | EPE: 6.65 -> 5.86 | Improved |
| Add intra- and inter-scene boundary contrastive losses (ablation) | HMBA-FlowNet with motion consistency adaptation · HR-KITTI | EPE: 6.89 -> 6.47 | Improved |
| Add intra-scene boundary contrastive loss (ablation) | HMBA-FlowNet with motion consistency and inter-scene boundary loss · LR-KITTI | EPE: 6.01 -> 5.86 | Improved |
| Add intra-scene boundary contrastive loss (ablation) | HMBA-FlowNet with motion consistency and inter-scene boundary loss · HR-KITTI | EPE: 6.54 -> 6.47 | Improved |
| Add inter-scene boundary contrastive loss (ablation) | HMBA-FlowNet with motion consistency and intra-scene boundary loss · LR-KITTI | EPE: 6.52 -> 5.86 | Improved |
| Add inter-scene boundary contrastive loss (ablation) | HMBA-FlowNet with motion consistency and intra-scene boundary loss · HR-KITTI | EPE: 6.67 -> 6.47 | Improved |
Closest papers by meaning
- End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning (NeurIPS 2024 · similarity 0.87)
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency (AAAI 2024 · similarity 0.87)
- Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow (ICLR 2024 · similarity 0.87)
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (AAAI 2024 · similarity 0.85)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.85)
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start (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.
