Research map / Detection and segmentation / CNN features
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
Limeng Qiao, Yuxuan Zhao, Zhiyuan Li, Xi Qiu, Jianan Wu, Chi Zhang
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 GDL in novel fine-tuning (GDL-N) (ablation) | Faster R-CNN · COCO novel FSOD, 10-shot | mAP: 7.9 -> 15.2 | Improved |
| add GDL in novel fine-tuning (GDL-N) (ablation) | Faster R-CNN · COCO novel FSOD, 30-shot | mAP: 12.2 -> 19.0 | Improved |
| add GDL in base training (GDL-B) (ablation) | Faster R-CNN · COCO novel FSOD, 10-shot | mAP: 7.9 -> 8.2 | Improved |
| add GDL in base training (GDL-B) on top of GDL-N (ablation) | Faster R-CNN + GDL-N · COCO novel FSOD, 10-shot | mAP: 15.2 -> 16.9 | Improved |
| add Prototypical Calibration Block (ablation) | Faster R-CNN · COCO novel FSOD, 10-shot | mAP: 7.9 -> 10.4 | Improved |
| add PCB on top of GDL-B and GDL-N (ablation) | DeFRCN · COCO novel FSOD, 10-shot | mAP: 16.9 -> 18.5 | Improved |
| add PCB to TFA (ablation) | TFA · COCO novel FSOD, 10-shot | mAP: 9.0 -> 11.8 | Improved |
| add PCB to MPSR (ablation) | MPSR · COCO novel FSOD, 30-shot | mAP: 14.5 -> 15.5 | Improved |
| add PCB to FRCN-ft (ablation) | FRCN-ft · COCO novel FSOD, 10-shot | mAP: 6.9 -> 9.9 | Improved |
| use stronger pre-trained model IG-WSL instead of IN-1K in PCB (ablation) | DeFRCN · VOC Novel Set 1, 10-shot | AP50: 60.8 -> 68.2 | Improved |
| use self-supervised IN-SwAV instead of IN-1K in PCB (ablation) | DeFRCN · VOC Novel Set 1, 10-shot | AP50: 60.8 -> 56.3 | Hurt |
| add GDL to conventional Faster R-CNN (ablation) | R50-C4-1x · COCO conventional detection | AP50: 56.1 -> 57.6 | Improved |
Later papers that compared with this method
21 later accepted papers report DeFRCN as a baseline in their results tables; 20 of them report a better number on most of the results they share with it.
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · better on 6 of 6 shared results)
- Adaptive Multi-task Learning for Few-shot Object Detection (ECCV 2024 · better on 2 of 2 shared results)
- SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation (CVPR 2024 · better on 1 of 1 shared result)
- UniFS: Universal Few-shot Instance Perception with Point Representations (ECCV 2024 · better on 1 of 1 shared result)
- Crowd-SAM:SAM as a smart annotator for object detection in crowded scenes (ECCV 2024 · better on 1 of 1 shared result)
- Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from a Conditional Causal Perspective (AAAI 2023 · better on 7 of 9 shared results)
- Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection (CVPR 2023 · better on 5 of 5 shared results)
- Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection (CVPR 2023 · better on 4 of 4 shared results)
13 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016 · similarity 0.91)
- Generalized Few-Shot Object Detection Without Forgetting (CVPR 2021 · similarity 0.90)
- Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning (ICCV 2019 · similarity 0.90)
- Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment (AAAI 2022 · similarity 0.90)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.89)
- Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective (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.
