--- title: "Faster R-CNN — Ren 2015" description: "By 2015, detectors such as SPPnet and Fast R-CNN had become fast enough that generating candidate object regions was the main cost at test time." authors: ["Shaoqing Ren", "Kaiming He", "Ross Girshick", "Jian Sun"] year: 2015 venue: "arXiv:1506.01497" source: "https://arxiv.org/abs/1506.01497" doi: "10.48550/arxiv.1506.01497" arxiv: "1506.01497" licence: "arXiv — non-exclusive license to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/ren-2015-faster-r-cnn-towards-real/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ren-2015-faster-r-cnn-towards-real/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/) / Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks # Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks **Authors:** Shaoqing Ren, [Kaiming He](https://md.research.elamur.ai/free/en/authors/kaiming-he/), [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/), Jian Sun · **Year:** 2015 · **Venue:** arXiv:1506.01497 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1506.01497) · [PDF](https://arxiv.org/pdf/1506.01497) · [DOI 10.48550/arxiv.1506.01497](https://doi.org/10.48550/arxiv.1506.01497) · [arXiv 1506.01497](https://arxiv.org/abs/1506.01497) · [OpenAlex](https://openalex.org/W639708223) **Citations:** 63924 citations (openalex-snapshot · 2026-10-14) · [819](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary By 2015, detectors such as SPPnet and Fast R-CNN had become fast enough that generating candidate object regions was the main cost at test time. These candidates usually came from hand-engineered CPU methods like Selective Search or EdgeBoxes. The authors replace that external step with a Region Proposal Network (RPN). The RPN is a small fully convolutional head that reuses the convolutional feature map the detector already computes. At every location, it scores and refines a set of "anchor" boxes with several scales and aspect ratios. Multi-scale handling therefore comes from reference boxes rather than image or filter pyramids. An alternating fine-tuning scheme lets the RPN and Fast R-CNN share convolutional layers, which yields one unified detector, Faster R-CNN. In it, the RPN works like an attention module that points to promising regions. On PASCAL VOC 2007/2012 and MS COCO, the system beats the Selective Search + Fast R-CNN baseline while making proposals nearly free. This made accurate, near-real-time deep detection practical and became a foundation for many later systems. ## Key points - **Speed:** Proposal cost drops to about 10 ms per image, compared with about 2 s for Selective Search (CPU) and 0.2 s for EdgeBoxes. The full VGG-16 pipeline runs at 5 fps on a GPU with only 300 proposals per image. - **RPN design:** A 3×3 window slides over the last shared conv layer and produces a 256-d (ZF) or 512-d (VGG-16) feature. Two sibling 1×1 layers follow: reg, which outputs 4k box coordinates, and cls, which outputs 2k object/not-object scores for k anchors. - **Backbones:** The authors test ZF (5 shareable conv layers) and VGG-16 (13 shareable conv layers). The window's effective receptive field is 171 px and 228 px respectively. - **Impact:** Faster R-CNN and RPN, combined with 101-layer ResNets, underpinned 1st-place entries at ILSVRC and COCO 2015 in ImageNet detection and localization and COCO detection and segmentation. The system was also deployed at Pinterest. - **Code and training:** Code is released in MATLAB (shaoqingren/faster_rcnn) and Python (rbgirshick/py-faster-rcnn). The authors also found that joint RPN + Fast R-CNN training works and shortens training time. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 819 papers of our library cite it (of the 140884 whose bibliographies we read); 32 of them have a page here, 787 not yet. - [Model Transfer for Event tracking as Transcript Understanding for Videos of Small Group Interaction](https://md.research.elamur.ai/free/en/papers/agarwal-2022-model-transfer-event-tracking-as/) - [Guided Open Vocabulary Image Captioning with Constrained Beam Search](https://md.research.elamur.ai/free/en/papers/anderson-2017-guided-open-vocabulary-image-captioning/) - [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/) - [Momentum Contrast for Unsupervised Visual Representation Learning](https://md.research.elamur.ai/free/en/papers/he-2019-momentum-contrast-unsupervised-visual-representation/) - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://md.research.elamur.ai/free/en/papers/howard-2017-mobilenets-efficient-convolutional-neural-networks/) - [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://md.research.elamur.ai/free/en/papers/huang-2022-layoutlmv3-pre-training-document-ai/) - [GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering](https://md.research.elamur.ai/free/en/papers/hudson-2019-gqa-new-dataset-real-world/) - [Probing Contextual Language Models for Common Ground with Visual Representations](https://md.research.elamur.ai/free/en/papers/ilharco-2021-probing-contextual-language-models-common/) - [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://md.research.elamur.ai/free/en/papers/kiela-2020-hateful-memes-challenge-detecting-hate/) - [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://md.research.elamur.ai/free/en/papers/kim-2021-vilt-vision-language-transformer-convolution/) - [Segment Anything](https://md.research.elamur.ai/free/en/papers/kirillov-2023-segment-anything/) - [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://md.research.elamur.ai/free/en/papers/krishna-2016-visual-genome-connecting-language-vision/) - [Referring Expressions with Rational Speech Act Framework: A Probabilistic Approach](https://md.research.elamur.ai/free/en/papers/le-2022-referring-expressions-rational-speech-act/) - [TVQA: Localized, Compositional Video Question Answering](https://md.research.elamur.ai/free/en/papers/lei-2018-tvqa-localized-compositional-video-question/) - [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://md.research.elamur.ai/free/en/papers/li-2019-visualbert-simple-performant-baseline-vision/) - [Dice Loss for Data-imbalanced NLP Tasks](https://md.research.elamur.ai/free/en/papers/li-2020-dice-loss-data-imbalanced-nlp/) - [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://md.research.elamur.ai/free/en/papers/li-2020-oscar-object-semantics-aligned-pre/) - [Focal Loss for Dense Object Detection](https://md.research.elamur.ai/free/en/papers/lin-2017-focal-loss-dense-object-detection/) - [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://md.research.elamur.ai/free/en/papers/liu-2023-grounding-dino-marrying-dino-grounded/) - [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://md.research.elamur.ai/free/en/papers/lu-2019-vilbert-pretraining-task-agnostic-visiolinguistic/) - [COMICORDA: Dialogue Act Recognition in Comic Books](https://md.research.elamur.ai/free/en/papers/martinek-2024-comicorda-dialogue-act-recognition-comic/) - [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/) - [DocVQA: A Dataset for VQA on Document Images](https://md.research.elamur.ai/free/en/papers/mathew-2020-docvqa-dataset-vqa-document-images/) - [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://md.research.elamur.ai/free/en/papers/su-2019-vl-bert-pre-training-generic/) - [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://md.research.elamur.ai/free/en/papers/tan-2019-lxmert-learning-cross-modality-encoder/) - [Multimodal Sarcasm Target Identification in Tweets](https://md.research.elamur.ai/free/en/papers/wang-2022-multimodal-sarcasm-target-identification-tweets/) - [A Comprehensive Survey on Graph Neural Networks](https://md.research.elamur.ai/free/en/papers/wu-2019-comprehensive-survey-graph-neural-networks/) - [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://md.research.elamur.ai/free/en/papers/xu-2019-layoutlm-pre-training-text-layout/) - [Modeling Context in Referring Expressions](https://md.research.elamur.ai/free/en/papers/yu-2016-modeling-context-referring-expressions/) - [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://md.research.elamur.ai/free/en/papers/yu-2022-coca-contrastive-captioners-image-text/) - [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://md.research.elamur.ai/free/en/papers/yue-2023-mmmu-massive-multi-discipline-multimodal/) - [Learning Transferable Architectures for Scalable Image Recognition](https://md.research.elamur.ai/free/en/papers/zoph-2017-learning-transferable-architectures-scalable-image/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{ren2015faster, title = {{Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks}}, author = {Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian}, year = {2015}, doi = {10.48550/arxiv.1506.01497}, eprint = {1506.01497}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1506.01497} } ``` - [← previous Fast Rhetorical Structure Theory Discourse Parsing](https://md.research.elamur.ai/free/en/papers/heilman-2015-fast-rhetorical-structure-theory-discourse/) - [next → FDTB1, première étape du projet « French Discourse Treebank » : repérage des connecteurs de discours en corpus](https://md.research.elamur.ai/free/en/papers/danlos-2015-fdtb1-premiere-etape-projet-french/) - [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/) ## References 3 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” in European Conference on Computer Vision (ECCV), 2014. [find](https://scholar.google.com/scholar?q=K%2E+He%2C+X%2E+Zhang%2C+S%2E+Ren%2C+and+J%2E+Sun%2C+%E2%80%9CSpatial+pyramid+pooling+in+deep+convolutional+networks+for+visual+recognition%2C%E2%80%9D+in+European+Conference+on+Computer+Vision+%28ECCV%29%2C+2014%2E) 2. R. Girshick, “Fast R-CNN,” in IEEE International Conference on Computer Vision (ICCV), 2015. [find](https://scholar.google.com/scholar?q=R%2E+Girshick%2C+%E2%80%9CFast+R%2DCNN%2C%E2%80%9D+in+IEEE+International+Conference+on+Computer+Vision+%28ICCV%29%2C+2015%2E) 3. K. Simonyan and A. Zisserman, “Very deep convolutional person : 0 .975 : 0. 958 : 0.823 person : 0.928 person person person : 0.941 person : 0.673 airplane : 0.997 person : 0.759 person : 0.766 backpack : 0.756 person : 0.939 person : 0.976 person : 0 .950 person : 0.805 handbag : 0.848 dog : 0.996… [find](https://scholar.google.com/scholar?q=K%2E+Simonyan+and+A%2E+Zisserman%2C+%E2%80%9CVery+deep+convolutional+person+%3A+0+%2E975+%3A+0%2E+958+%3A+0%2E823+person+%3A+0%2E928+person+person+person+%3A+0%2E941+person+%3A+0%2E673+airplane+%3A+0%2E997+person+%3A+0%2E759+person+%3A+0%2E766+backpa)