Research map / Detection and segmentation / Open-set and few-shot detection
Dual Domain Control via Active Learning for Remote Sensing Domain Incremental Object Detection
Jiachen Sun, De Cheng, Xi Yang, Nannan Wang
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 ALER example replay (ablation) | Active-DDC · Sequence I joint test | mAP: 31.3 -> 34.7 | Improved |
| add ADSC query distillation (ablation) | Active-DDC · Sequence I joint test | mAP: 31.3 -> 33.9 | Improved |
| add ADSC on top of ALER (ablation) | Active-DDC · Sequence I joint test | mAP: 34.7 -> 36.2 | Improved |
| add ALER and ADSC (ablation) | Active-DDC · Sequence I joint test | AP50: 60.3 -> 67.8 | Improved |
| add ALER (ablation) | Active-DDC · Sequence II joint test | mAP: 24.5 -> 29.1 | Improved |
| add ADSC (ablation) | Active-DDC · Sequence II joint test | mAP: 24.5 -> 28.3 | Improved |
| add ALER and ADSC (ablation) | Active-DDC · Sequence II joint test | mAP: 24.5 -> 32.7 | Improved |
| replace ER replay with ALER (ablation) | Replay module · Joint test | AP50: 61.1 -> 65.1 | Improved |
| replace RPC replay with ALER (ablation) | Replay module · Joint test | AP50: 64.7 -> 65.1 | Improved |
| replace KD-DETR distillation with ADSC (ablation) | Distillation module · Joint test | AP50: 63.4 -> 64.0 | Improved |
| replace DETRDistill with ADSC (ablation) | Distillation module · Joint test | AP50: 61.0 -> 64.0 | Improved |
| apply Active-DDC instead of fine-tuning on Sequence III (ablation) | Active-DDC · Sequence III joint test | accuracy (AP50): 36.6 -> 42.5 | Improved |
Closest papers by meaning
- Active Domain Adaptation with False Negative Prediction for Object Detection (CVPR 2024 · similarity 0.85)
- ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks (CVPR 2026 · similarity 0.85)
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS 2025 · similarity 0.85)
- ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object (CVPR 2025 · similarity 0.84)
- Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees (AAAI 2024 · similarity 0.84)
- AS-Det: Active Sampling for Adaptive 3D Object Detection in Point Clouds (AAAI 2025 · similarity 0.84)
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.
