Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
The DOI matches its Crossref record; 78 of the 83 references it cites were found in a registry or an index.
Abstract
Object detection performance, as measured on the canonical PASCAL VOC Challenge datasets, plateaued in the final years of the competition. The best-performing methods were complex ensemble systems that typically combined multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 50 percent relative to the previous best result on VOC 2012-achieving a mAP of 62.4 percent. Our approach combines two ideas: (1) one can apply high-capacity convolutional networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data are scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, boosts performance significantly. Since we combine region proposals with CNNs, we call the resulting model an R-CNN or Region-based Convolutional Network. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“for example, for AlexNet pretrained on ImageNet, FC6 / FC7 / Pool5 are in descending order of detection accuracy (Donahue et al. 2014;Girshick et al. 2016).”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Girshick et al. 2016
In the citing paper
“Fine-tuning a pre-trained network can increase detection performance significantly (Girshick et al. 2014(Girshick et al. , 2016))”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Girshick et al. 2016
In the citing paper
“although in the case of AlexNet, the fine-tuning performance boost was shown to be much larger for FC6 / FC7 than for Pool5, suggesting that Pool5 features are more general.”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Girshick et al. 2016
In the citing paper
“Pretrained CNNs without fine-tuning were explored for object classification and detection in Donahue et al. (2014), Girshick et al. (2016), Agrawal et al. (2014), where it was shown that detection accuracies are different for features extracted from different layers”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Girshick et al. 2016
In the citing paper
“For detection, the pre-trained network is typically fine-tunedfoot_7 on a given detection dataset (Donahue et al. 2014;Girshick et al. 2014Girshick et al. , 2016)).”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Girshick et al. 2016
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Self-citationHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Self-citation
Research works printed but not linked: 3
- girshick, 0, Fast R-CNN, ArXiv e-prints
- dalal, 0, Proc IEEE Conf Comput Vis Pattern Recognit, 886
- 10.1109/cvpr.2013.237 · DOI · Paper page
Cited by
Items 1,001–1,006 of 1,006
Hierarchical object detection for very high-resolution satellite images
Wu, Z.-Z., Wang, X.-F., Zou, L., Xu, L.-X., Li, X.-L., & Weise, T. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107885 · Cited by 18
Ham, S. W., Park, H.-C., Kim, E.-J., Kho, S.-Y., & Kim, D.-K. (2020) · Transportation Research Record: Journal of the Transportation Research Board · doi:10.1177/0361198120954187 · Cited by 9
YOLO Algorithms Performance Comparison for Object Detection in Adverse Weather Conditions
Haimer, Z., Mateur, K., Farhan, Y., & Madi, A. A. (2023) · 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset57153.2023.10152924 · Cited by 6
“When applied to real-time data, R-CNN [6] showed better accuracy as compared to R-FCN [5] which yielded more speed.”
MethodAn Improved YOLOv5-based Method for Surface Defect Detection of Steel Plate
Zhu, L., Zhang, J., & Jia, C. (2022) · 2022 China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055055 · Cited by 6
Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection
Llerena, J. M., Zeni, L. F., Kristen, L. N., & Jung, C. (2021) · arXiv · doi:10.48550/arxiv.2106.06072 · Cited by 5
Ci, J., Tan, H., Zhai, H., & Tang, X. (2024) · Remote Sensing · doi:10.3390/rs16162953 · Cited by 4
Metadata
- Authors
- Girshick, R., Donahue, J., Darrell, T., & Malik, J.
- Affiliations
- Microsoft (United States) (US)
- University of California, Berkeley (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2016-01-01
- Volume
- 38
- Issue
- 1
- Pages
- 142-158
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2183182206
- Cited by
- 2,912
- References
- 83
- Citations by year
- 2026: 121 · 2025: 304 · 2024: 298 · 2023: 352 · 2022: 316 · 2021: 363 · 2020: 334 · 2019: 303 · 2018: 261 · 2017: 175 · 2016: 81
- FWCI
- 150.45
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Funders
- US National Science Foundation (IIS-0905647, IIS-1134072, IIS-1212798, MURI N000014-10-1-0933)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- object detection, semantic segmentation, R-CNN, region proposal, convolutional neural networks, fine-tuning, mean average precision
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.