Research map / Detection and segmentation / Open-set and few-shot detection
Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning
Yan Li, Weiwei Guo, Xue Yang, Ning Liao, Dunyun He, Jiaqi Zhou, Wenxian Yu
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 RemoteCLIP external teacher to student plus localization teacher (ablation) | CastDet · VisDroneZSD | mAR novel: 47.7 -> 69.1 | Improved |
| add EMA localization teacher to supervised student (ablation) | CastDet · VisDroneZSD | mAR novel: 24.7 -> 47.7 | Improved |
| select pseudo boxes by regression jittering variance instead of RPN score (ablation) | CastDet · VisDroneZSD | mAP novel: 43.3 -> 47.8 | Improved |
| select pseudo boxes by box jittering variance instead of RPN score (ablation) | CastDet · VisDroneZSD | mAP novel: 43.3 -> 43.6 | No clear effect |
| add dynamic label queue with dynamic updating (ablation) | CastDet · VisDroneZSD | mAP: 11.6 -> 39.5 | Improved |
| reduce labeled data from 100% to 34% (ablation) | CastDet · VisDroneZSD | mAP: 39.5 -> 38.6 | No clear effect |
| replace direct RemoteCLIP classification with CastDet training on RPN proposals | RemoteCLIP · VisDroneZSD (RPN proposals) | mAP: 11.6 -> 38.1 | Improved |
| replace direct CLIP classification with CastDet on ground-truth proposals | CLIP · VisDroneZSD (GT proposals) | mAP novel: 66.4 -> 49.9 | Hurt |
| use CastDet instead of best prior OVD detector | OV-DETR · VisDroneZSD | mAP novel: 25.5 -> 46.5 | Improved |
| use CastDet instead of GLIP on base categories | GLIP · VisDroneZSD | mAP base: 41.0 -> 36.5 | Hurt |
Closest papers by meaning
- VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection (AAAI 2026 · similarity 0.92)
- Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community (AAAI 2025 · similarity 0.89)
- Taming Self-Training for Open-Vocabulary Object Detection (CVPR 2024 · similarity 0.89)
- Simple Image-Level Classification Improves Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.88)
- Open-Det: An Efficient Learning Framework for Open-Ended Detection (ICML 2025 · similarity 0.87)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · 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.
