Research map / Detection and segmentation / CNN features
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
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 |
|---|---|---|---|
| share conv layers between RPN and Fast R-CNN (ablation) | Faster R-CNN ZF · VOC07 test | mAP: 58.7 -> 59.9 | Improved |
| add cls scores for ranking proposals (vs random sampling) at N=100 (ablation) | RPN+ZF · VOC07 test | mAP: 44.6 -> 55.1 | Improved |
| add reg layer (vs anchor boxes as proposals) (ablation) | RPN+ZF · VOC07 test | mAP: 52.1 -> 56.8 | Improved |
| apply NMS to proposals (ablation) | RPN+ZF · VOC07 test | mAP: 55.2 -> 56.8 | No clear effect |
| replace ZF with VGG-16 in RPN (ablation) | RPN · VOC07 test (SS-trained ZF detector) | mAP: 56.8 -> 59.2 | Improved |
| replace SS with RPN in train and test (ablation) | Fast R-CNN ZF · VOC07 test | mAP: 58.7 -> 59.9 | Improved |
| use shared features for VGG-16 (ablation) | Faster R-CNN VGG-16 · VOC07 test | mAP: 68.5 -> 69.9 | Improved |
| add VOC12 trainval to training | Faster R-CNN VGG-16 · VOC07 test | mAP: 69.9 -> 73.2 | Improved |
| add COCO pretraining to VOC07+12 | Faster R-CNN VGG-16 · VOC07 test | mAP: 73.2 -> 78.8 | Improved |
| add multiple scales (3 scales, 1 ratio vs 1 scale 1 ratio) (ablation) | Faster R-CNN VGG-16 · VOC07 test | mAP: 66.7 -> 69.8 | Improved |
| add multiple aspect ratios (3 ratios, 128^2 scale) (ablation) | Faster R-CNN VGG-16 · VOC07 test | mAP: 65.8 -> 68.8 | Improved |
| add 3 aspect ratios to 3 scales (ablation) | Faster R-CNN VGG-16 · VOC07 test | mAP: 69.8 -> 69.9 | No clear effect |
Later papers that compared with this method
175 later accepted papers report Faster R-CNN as a baseline in their results tables; 164 of them report a better number on most of the results they share with it.
- Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection (TPAMI 2026 · better on 4 of 4 shared results)
- DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection (ICML 2026 · better on 2 of 2 shared results)
- InfoDet: A Dataset for Infographic Element Detection (ICLR 2026 · better on 2 of 2 shared results)
- VLM4RSDet: Collaborative Optimization with Vision-Language Model for Enhancing Remote Sensing Object Detection (CVPR 2026 · better on 1 of 2 shared results)
- Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection (AAAI 2026 · better on 2 of 2 shared results)
- CerDETR: Cell-Prior Empowered DETR for Cervical Lesion Detection (ECCV 2026 · better on 2 of 2 shared results)
- SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection (ICML 2026 · better on 1 of 1 shared result)
- Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization (CVPR 2026 · better on 1 of 1 shared result)
167 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
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.94)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · similarity 0.93)
- CoupleNet: Coupling Global Structure With Local Parts for Object Detection (ICCV 2017 · similarity 0.92)
- HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection (CVPR 2016 · similarity 0.92)
- Sparse R-CNN: An End-to-End Framework for Object Detection (TPAMI 2023 · similarity 0.91)
- Sparse R-CNN: End-to-End Object Detection With Learnable Proposals (CVPR 2021 · similarity 0.91)
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.
