AI Paper Atlas

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

AAAI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Transfer clean-domain motion with hierarchical motion and boundary adaptationOptical flow estimation under adverse weather · LR-KITTIEPE: 6.98 -> 5.86Improved
Transfer clean-domain motion with hierarchical motion and boundary adaptationOptical flow estimation under adverse weather · HR-KITTIEPE: 6.95 -> 6.47Improved
Transfer clean-domain motion with hierarchical motion and boundary adaptationOptical flow estimation under adverse weather · GOF RainEPE: 1.07 -> 0.91Improved
Transfer clean-domain motion with hierarchical motion and boundary adaptationOptical flow estimation under adverse weather · GOF FogEPE: 0.95 -> 0.84Improved
Add flow consistency and feature alignment (ablation)HMBA-FlowNet · LR-KITTIEPE: 9.14 -> 6.65Improved
Add flow consistency and feature alignment (ablation)HMBA-FlowNet · HR-KITTIEPE: 10.61 -> 6.89Improved
Add intra- and inter-scene boundary contrastive losses (ablation)HMBA-FlowNet with motion consistency adaptation · LR-KITTIEPE: 6.65 -> 5.86Improved
Add intra- and inter-scene boundary contrastive losses (ablation)HMBA-FlowNet with motion consistency adaptation · HR-KITTIEPE: 6.89 -> 6.47Improved
Add intra-scene boundary contrastive loss (ablation)HMBA-FlowNet with motion consistency and inter-scene boundary loss · LR-KITTIEPE: 6.01 -> 5.86Improved
Add intra-scene boundary contrastive loss (ablation)HMBA-FlowNet with motion consistency and inter-scene boundary loss · HR-KITTIEPE: 6.54 -> 6.47Improved
Add inter-scene boundary contrastive loss (ablation)HMBA-FlowNet with motion consistency and intra-scene boundary loss · LR-KITTIEPE: 6.52 -> 5.86Improved
Add inter-scene boundary contrastive loss (ablation)HMBA-FlowNet with motion consistency and intra-scene boundary loss · HR-KITTIEPE: 6.67 -> 6.47Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy