Research map / Detection and segmentation / Open-set and few-shot detection
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
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 |
|---|---|---|---|
| Add region-level prediction consistency to source-only detection (ablation) | Faster R-CNN cross-domain detection · Foggy Cityscapes val | mAP: 26.9 -> 34.2 | Helped |
| Add inter-graph consistency to region-level consistency (ablation) | MTOR_R · Foggy Cityscapes val | mAP: 34.2 -> 34.5 | Helped |
| Add intra-graph consistency to region-level consistency (ablation) | MTOR_R · Foggy Cityscapes val | mAP: 34.2 -> 34.9 | Helped |
| Add both inter-graph and intra-graph consistency (ablation) | MTOR_R · Foggy Cityscapes val | mAP: 34.2 -> 35.1 | Helped |
| Add inter-graph consistency to region-level consistency (ablation) | MTOR_R · Cityscapes val (SIM10k → Cityscapes) | car AP: 45.9 -> 46.1 | Helped |
| Add intra-graph consistency to region-level consistency (ablation) | MTOR_R · Cityscapes val (SIM10k → Cityscapes) | car AP: 45.9 -> 46.3 | Helped |
| Add both inter-graph and intra-graph consistency (ablation) | MTOR_R · Cityscapes val (SIM10k → Cityscapes) | car AP: 45.9 -> 46.6 | Helped |
| Add inter-graph consistency to region-level consistency (ablation) | MTOR_R · COCO val (Syn2Real synthetic → real) | mAP: 19.3 -> 19.6 | Helped |
| Add intra-graph consistency to region-level consistency (ablation) | MTOR_R · COCO val (Syn2Real synthetic → real) | mAP: 19.3 -> 20.0 | Helped |
| Add both inter-graph and intra-graph consistency (ablation) | MTOR_R · COCO val (Syn2Real synthetic → real) | mAP: 19.3 -> 20.7 | Helped |
| Tune consistency-loss tradeoff weight and teacher EMA smoothing coefficient (ablation) | MTOR · Cityscapes → Foggy Cityscapes | mAP | Mixed |
Closest papers by meaning
- Unbiased Mean Teacher for Cross-Domain Object Detection (CVPR 2021 · similarity 0.91)
- Cross-Domain Adaptive Teacher for Object Detection (CVPR 2022 · similarity 0.91)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.89)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.88)
- D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection (CVPR 2024 · similarity 0.86)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (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.