Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Adaptive Teacher for Object 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 adversarial feature alignment with Ldis (ablation) | Adaptive Teacher · Clipart1k | mAP: 40.6 (-8.7) -> 49.3 (+4.3) | Helped |
| Add adversarial feature alignment with Ldis (ablation) | Adaptive Teacher · Watercolor2k | mAP: 55.5 (-4.4) -> 59.9 (+9.3) | Helped |
| Add adversarial feature alignment with Ldis (ablation) | Adaptive Teacher · Foggy Cityscapes | mAP: 48.7 (-2.2) -> 50.9 (+8.2) | Helped |
| Use weak augmentation for the teacher and strong augmentation for the student (ablation) | Adaptive Teacher · Clipart1k | mAP: 45.3 (-4.0) -> 49.3 (+4.3) | Helped |
| Use weak augmentation for the teacher and strong augmentation for the student (ablation) | Adaptive Teacher · Watercolor2k | mAP: 55.1 (-4.8) -> 59.9 (+9.3) | Helped |
| Use weak augmentation for the teacher and strong augmentation for the student (ablation) | Adaptive Teacher · Foggy Cityscapes | mAP: 45.9 (-5.0) -> 50.9 (+8.2) | Helped |
| Add target pseudo-label training and teacher EMA mutual learning (ablation) | Adaptive Teacher · Clipart1k | mAP: 31.6 (-17.7) -> 49.3 (+4.3) | Helped |
| Add target pseudo-label training and teacher EMA mutual learning (ablation) | Adaptive Teacher · Watercolor2k | mAP: 50.2 (-9.7) -> 59.9 (+9.3) | Helped |
| Add target pseudo-label training and teacher EMA mutual learning (ablation) | Adaptive Teacher · Foggy Cityscapes | mAP: 36.0 (-14.9) -> 50.9 (+8.2) | Helped |
| Use Adaptive Teacher instead of UMT | Cross-domain object detection · Clipart1k test | mAP: 44.1 (-0.9) -> 49.3 (+4.3) | Helped |
| Use Adaptive Teacher instead of UMT | Cross-domain object detection · Watercolor2k test | mAP: 58.1 (+7.5) -> 59.9 (+9.3) | Helped |
| Use Adaptive Teacher instead of UMT | Cross-domain object detection · Foggy Cityscapes test | mAP: 41.7 (-1.0) -> 50.9 (+8.2) | Helped |
Closest papers by meaning
- Unbiased Mean Teacher for Cross-Domain Object Detection (CVPR 2021 · similarity 0.93)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.93)
- Expert-Teacher-Student Collaborative Learning for Domain Adaptive Object Detection (CVPR 2026 · similarity 0.93)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.92)
- D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection (CVPR 2024 · similarity 0.91)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.91)
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.