Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation
Check 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 CCDistill with cross-domain content and style distillation | RefineNet for nighttime segmentation · Dark Zurich-test | mIoU: 44.3 -> 47.5 | Helped |
| Use CCDistill with cross-domain content and style distillation | RefineNet for nighttime segmentation · ACDC-night-val | mIoU: 37.0 -> 37.7 | Helped |
| Use CCDistill trained for Dark Zurich rather than MGCDA | Nighttime segmentation evaluated across datasets · BDD100K-night | mIoU: 34.9 -> 33.0 | Hurt |
| Add cross-domain content distillation (CDC) (ablation) | CCDistill · Dark Zurich-test | mIoU: 45.3 -> 47.5 | Helped |
| Add a project head to map CDC features into a common embedding space (ablation) | CCDistill · Dark Zurich-test | mIoU: 38.2 -> 47.5 | Helped |
| Add the JS-divergence loss to CDC (ablation) | CCDistill · Dark Zurich-test | mIoU: 44.6 -> 47.5 | Helped |
| Add illuminance correlation to CDC (ablation) | CCDistill · Dark Zurich-test | mIoU: 45.7 -> 47.5 | Helped |
| Add inherent correlation to CDC (ablation) | CCDistill · Dark Zurich-test | mIoU: 45.9 -> 47.5 | Helped |
| Add cross-domain style distillation (CDS) (ablation) | CCDistill · Dark Zurich-test | mIoU: 44.0 -> 47.5 | Helped |
| Add LAB-based image translation (ablation) | CCDistill · Dark Zurich-test | mIoU: 43.5 -> 47.5 | Helped |
| Add both CDC and CDS (ablation) | CCDistill without CDC and CDS · Dark Zurich-test | mIoU: 44.8 -> 47.5 | Helped |
Closest papers by meaning
- The Parables of the Mustard Seed and the Yeast: Extremely Low-Budget, High-Performance Nighttime Semantic Segmentation (AAAI 2025 · similarity 0.89)
- Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow (ICLR 2024 · similarity 0.87)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Day-Night Cross-domain Vehicle Re-identification (CVPR 2024 · similarity 0.85)
- NightCC: Nighttime Color Constancy via Adaptive Channel Masking (CVPR 2024 · similarity 0.85)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · 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.