Research map / Detection and segmentation / Open-set and few-shot detection
Unbiased Mean Teacher for Cross-Domain 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 cross-domain distillation using source-like target images for the teacher and target images for the student (ablation) | Mean Teacher for cross-domain object detection · PASCAL VOC→Clipart1k test | mAP: 33.6 -> 37.6 | Helped |
| Add target-like source images as labeled student training data (ablation) | Mean Teacher with cross-domain distillation · PASCAL VOC→Clipart1k test | mAP: 37.6 -> 41.8 | Helped |
| Select distillation samples using out-of-distribution confidence estimates (ablation) | UMT_SCA · PASCAL VOC→Clipart1k test | mAP: 41.8 -> 44.1 | Helped |
| Add cross-domain distillation using source-like target images for the teacher and target images for the student (ablation) | Mean Teacher for cross-domain object detection · Cityscapes→Foggy Cityscapes validation | mAP: 28.5 -> 39.2 | Helped |
| Add target-like source images as labeled student training data (ablation) | Mean Teacher with cross-domain distillation · Cityscapes→Foggy Cityscapes validation | mAP: 39.2 -> 40.4 | Helped |
| Select distillation samples using out-of-distribution confidence estimates (ablation) | UMT_SCA · Cityscapes→Foggy Cityscapes validation | mAP: 40.4 -> 41.7 | Helped |
| Add cross-domain distillation using source-like target images for the teacher and target images for the student (ablation) | Mean Teacher for cross-domain object detection · SIM10K→Cityscapes validation | AP (car): 40.8 -> 42.0 | Helped |
| Add target-like source images as labeled student training data (ablation) | Mean Teacher with cross-domain distillation · SIM10K→Cityscapes validation | AP (car): 42.0 -> 42.6 | Helped |
| Select distillation samples using out-of-distribution confidence estimates (ablation) | UMT_SCA · SIM10K→Cityscapes validation | AP (car): 42.6 -> 43.1 | Helped |
| Use simple mean teacher instead of source-only training (ablation) | Object detection for cross-domain adaptation · PASCAL VOC→Clipart1k test | mAP: 27.7 -> 33.6 | Helped |
Closest papers by meaning
- Cross-Domain Adaptive Teacher for Object Detection (CVPR 2022 · similarity 0.93)
- Exploring Object Relation in Mean Teacher for Cross-Domain Detection (CVPR 2019 · 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 0.89)
- Non-exemplar Domain Incremental Object Detection via Learning Domain Bias (AAAI 2024 · similarity 0.88)
- D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection (CVPR 2024 · similarity 0.87)
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.