Research map / Detection and segmentation / Open-set and few-shot detection
Dual-Rate Dynamic Teacher for Source-Free Domain Adaptive Object Detection
Qi He, Xiao Wu, Jun-Yan He, Shuai Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add integration of teacher and student pseudo-labels (ablation) | Mean Teacher + MIC · Foggy ablation | mAP: 39.8 -> 41.3 | Improved |
| add AEMA dual-rate teacher update (ablation) | Mean Teacher + MIC · Foggy ablation | mAP: 39.8 -> 44.6 | Improved |
| add integration and AEMA together (ablation) | Mean Teacher + MIC · Foggy ablation | mAP: 39.8 -> 45.5 | Improved |
| add MIC module to integration and AEMA (ablation) | DDT · Foggy ablation | mAP: 43.2 -> 45.5 | Improved |
| use teacher gradient instead of student gradient for grouping (ablation) | AEMA · Foggy ablation | mAP: 45.3 -> 45.5 | Improved |
| select 10% instead of 20% target-responsive parameters (ablation) | AEMA · Foggy ablation | mAP: 44.3 -> 45.5 | Improved |
| select 10% instead of 5% target-responsive parameters (ablation) | AEMA · Foggy ablation | mAP: 45.1 -> 45.5 | Improved |
| use ths=0.5, tht=0.4 instead of ths=0.5, tht=0.5 (ablation) | DDT · Foggy ablation | mAP: 42.9 -> 45.5 | Improved |
| use two groups instead of one (ablation) | AEMA · Foggy ablation | mAP: 41.3 -> 45.5 | Improved |
| use three groups instead of two (ablation) | AEMA · Foggy ablation | mAP: 45.5 -> 44.7 | Hurt |
| use four groups instead of two (ablation) | AEMA · Foggy ablation | mAP: 45.5 -> 44.0 | Hurt |
| add AEMA to TransDA | TransDA · VisDA (SFDA) | average accuracy: 83.0 -> 84.2 | Improved |
Closest papers by meaning
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.88)
- Test-Time Adaptive Object Detection with Foundation Model (NeurIPS 2025 · similarity 0.87)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.87)
- D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection (CVPR 2024 · similarity 0.87)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.86)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · 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.
