---
title: "Rich feature hierarchies for accurate object — Girshick 2013"
description: "Progress in object detection on PASCAL VOC had stalled around 2010–2012, with leading systems relying on hand-crafted features such as SIFT and HOG and…"
authors: ["Ross Girshick", "Jeff Donahue", "Trevor Darrell", "Jitendra Malik"]
year: 2013
venue: "arXiv:1311.2524"
source: "https://arxiv.org/abs/1311.2524"
doi: "10.48550/arxiv.1311.2524"
arxiv: "1311.2524"
licence: "arXiv — non-exclusive licence 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/girshick-2013-rich-feature-hierarchies-accurate-object/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/girshick-2013-rich-feature-hierarchies-accurate-object/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/) / Rich feature hierarchies for accurate object detection and semantic segmentation

# Rich feature hierarchies for accurate object detection and semantic segmentation

**Authors:** [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/), [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/), [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-darrell/), Jitendra Malik · **Institutions:** [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · **Year:** 2013 · **Venue:** arXiv:1311.2524 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1311.2524) · [PDF](https://arxiv.org/pdf/1311.2524) · [DOI 10.48550/arxiv.1311.2524](https://doi.org/10.48550/arxiv.1311.2524) · [arXiv 1311.2524](https://arxiv.org/abs/1311.2524) · [OpenAlex](https://openalex.org/W2102605133)

**Citations:** 31477 citations (OpenAlex, 2026-10-14) · [238](https://md.research.elamur.ai/free/en/papers/girshick-2013-rich-feature-hierarchies-accurate-object/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Progress in object detection on PASCAL VOC had stalled around 2010–2012, with leading systems relying on hand-crafted features such as SIFT and HOG and on elaborate ensembles. Girshick et al. ask whether the CNN breakthrough in ImageNet classification carries over to detection. Their system, R-CNN, takes about 2000 class-agnostic candidate regions from selective search. It warps each region to a fixed 227×227 input and passes it through a Krizhevsky-style CNN (implemented in Caffe) to get a 4096-dimensional descriptor. Per-class linear SVMs then score each region.

To cope with the small amount of labelled detection data, the network is first trained for classification on ILSVRC2012 and then fine-tuned on PASCAL. A class-specific bounding-box regressor corrects localization errors. R-CNN reaches 53.3% mAP on VOC 2012, more than 30% better in relative terms than the previous best. It also beats OverFeat on ILSVRC2013 detection and gives competitive semantic segmentation results. The work established region-based deep detection and the pre-train-then-fine-tune recipe as standard practice.

## Key points
- **VOC 2010:** R-CNN reaches 53.7% mAP, compared with 33.4% for HOG-based DPM and 35.1% for the UVA system, which uses the same proposals with bag-of-visual-words features.
- **ILSVRC2013 detection (200 classes):** R-CNN scores 31.4% mAP, against 24.3% for the sliding-window OverFeat detector.
- **Fine-tuning:** Domain-specific fine-tuning after ILSVRC2012 pre-training adds about 8 mAP points.
- **Efficiency:** Region features are shared across classes and are compact (4k dimensions, versus 360k for UVA). Proposals and features take about 13 s per image on a GPU, so the approach scales to thousands of classes.
- **Semantic segmentation:** R-CNN reaches 47.9% average accuracy on the VOC 2011 test set. Later versions of the paper add results with the 16-layer Simonyan–Zisserman network.

*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/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{girshick2013rich,
  title = {{Rich feature hierarchies for accurate object detection and semantic segmentation}},
  author = {Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
  year = {2013},
  doi = {10.48550/arxiv.1311.2524},
  eprint = {1311.2524},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1311.2524}
}
```

- [next → Auto-Encoding Variational Bayes](https://md.research.elamur.ai/free/en/papers/kingma-2013-auto-encoding-variational-bayes/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/)

## References

28 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. B. Alexe, T. Deselaers, and V. Ferrari. Measuring the objectness of image windows. TPAMI, 2012. 2 [find](https://scholar.google.com/scholar?q=B%2E+Alexe%2C+T%2E+Deselaers%2C+and+V%2E+Ferrari%2E+Measuring+the+objectness+of+image+windows%2E+TPAMI%2C+2012%2E+2)
2. P. Arbeláez, B. Hariharan, C. Gu, S. Gupta, L. Bourdev, and J. Malik. Semantic segmentation using regions and parts. In CVPR, 2012. 10, 11 [find](https://scholar.google.com/scholar?q=P%2E+Arbela%CC%81ez%2C+B%2E+Hariharan%2C+C%2E+Gu%2C+S%2E+Gupta%2C+L%2E+Bourdev%2C+and+J%2E+Malik%2E+Semantic+segmentation+using+regions+and+parts%2E+In+CVPR%2C+2012%2E+10%2C+11)
3. P. Arbeláez, J. Pont-Tuset, J. Barron, F. Marques, and J. Malik. Multiscale combinatorial grouping. In CVPR, 2014. 3 [find](https://scholar.google.com/scholar?q=P%2E+Arbela%CC%81ez%2C+J%2E+Pont%2DTuset%2C+J%2E+Barron%2C+F%2E+Marques%2C+and+J%2E+Malik%2E+Multiscale+combinatorial+grouping%2E+In+CVPR%2C+2014%2E+3)
4. J. Carreira, R. Caseiro, J. Batista, and C. Sminchisescu. Semantic segmentation with second-order pooling. In ECCV, 2012. 4, 10, 11, 13, 14 [find](https://scholar.google.com/scholar?q=J%2E+Carreira%2C+R%2E+Caseiro%2C+J%2E+Batista%2C+and+C%2E+Sminchisescu%2E+Semantic+segmentation+with+second%2Dorder+pooling%2E+In+ECCV%2C+2012%2E+4%2C+10%2C+11%2C+13%2C+14)
5. J. Carreira and C. Sminchisescu. CPMC: Automatic object segmentation using constrained parametric min-cuts. TPAMI, 2012. 2, 3 [find](https://scholar.google.com/scholar?q=J%2E+Carreira+and+C%2E+Sminchisescu%2E+CPMC%3A+Automatic+object+segmentation+using+constrained+parametric+min%2Dcuts%2E+TPAMI%2C+2012%2E+2%2C+3)
6. D. Cireşan, A. Giusti, L. Gambardella, and J. Schmidhuber. Mitosis detection in breast cancer histology images with deep neural networks. In MICCAI, 2013. 3 [find](https://scholar.google.com/scholar?q=D%2E+Cires%CC%A7an%2C+A%2E+Giusti%2C+L%2E+Gambardella%2C+and+J%2E+Schmidhuber%2E+Mitosis+detection+in+breast+cancer+histology+images+with+deep+neural+networks%2E+In+MICCAI%2C+2013%2E+3)
7. N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 1 [find](https://scholar.google.com/scholar?q=N%2E+Dalal+and+B%2E+Triggs%2E+Histograms+of+oriented+gradients+for+human+detection%2E+In+CVPR%2C+2005%2E+1)
8. T. Dean, M. A. Ruzon, M. Segal, J. Shlens, S. Vijayanarasimhan, and J. Yagnik. Fast, accurate detection of 100,000 object classes on a single machine. In CVPR, 2013. 3 [find](https://scholar.google.com/scholar?q=T%2E+Dean%2C+M%2E+A%2E+Ruzon%2C+M%2E+Segal%2C+J%2E+Shlens%2C+S%2E+Vijayanarasimhan%2C+and+J%2E+Yagnik%2E+Fast%2C+accurate+detection+of+100%2C000+object+classes+on+a+single+machine%2E+In+CVPR%2C+2013%2E+3)
9. J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, and L. Fei-Fei. ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC2012). [http://www.image-net.org/challenges/LSVRC/2012/](http://www.image-net.org/challenges/LSVRC/2012/). 1 [↗](http://www.image-net.org/challenges/LSVRC/2012/)
10. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A large-scale hierarchical image database. In CVPR, 2009. 1 [find](https://scholar.google.com/scholar?q=J%2E+Deng%2C+W%2E+Dong%2C+R%2E+Socher%2C+L%2E%2DJ%2E+Li%2C+K%2E+Li%2C+and+L%2E+Fei%2DFei%2E+ImageNet%3A+A+large%2Dscale+hierarchical+image+database%2E+In+CVPR%2C+2009%2E+1)
11. J. Deng, O. Russakovsky, J. Krause, M. Bernstein, A. C. Berg, and L. Fei-Fei. Scalable multi-label annotation. In CHI, 2014. 8 [find](https://scholar.google.com/scholar?q=J%2E+Deng%2C+O%2E+Russakovsky%2C+J%2E+Krause%2C+M%2E+Bernstein%2C+A%2E+C%2E+Berg%2C+and+L%2E+Fei%2DFei%2E+Scalable+multi%2Dlabel+annotation%2E+In+CHI%2C+2014%2E+8)
12. J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In ICML, 2014. 2 [find](https://scholar.google.com/scholar?q=J%2E+Donahue%2C+Y%2E+Jia%2C+O%2E+Vinyals%2C+J%2E+Hoffman%2C+N%2E+Zhang%2C+E%2E+Tzeng%2C+and+T%2E+Darrell%2E+DeCAF%3A+A+Deep+Convolutional+Activation+Feature+for+Generic+Visual+Recognition%2E+In+ICML%2C+2014%2E+2)
13. M. Douze, H. Jégou, H. Sandhawalia, L. Amsaleg, and C. Schmid. Evaluation of gist descriptors for web-scale image search. In Proc. of the ACM International Conference on Image and Video Retrieval, 2009. 13 [find](https://scholar.google.com/scholar?q=M%2E+Douze%2C+H%2E+Je%CC%81gou%2C+H%2E+Sandhawalia%2C+L%2E+Amsaleg%2C+and+C%2E+Schmid%2E+Evaluation+of+gist+descriptors+for+web%2Dscale+image+search%2E+In+Proc%2E+of+the+ACM+International+Conference+on+Image+and+Video+Retrieval%2C+20)
14. I. Endres and D. Hoiem. Category independent object proposals. In ECCV, 2010. 3 [find](https://scholar.google.com/scholar?q=I%2E+Endres+and+D%2E+Hoiem%2E+Category+independent+object+proposals%2E+In+ECCV%2C+2010%2E+3)
15. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes (VOC) Challenge. IJCV, 2010. 1, 4 [find](https://scholar.google.com/scholar?q=M%2E+Everingham%2C+L%2E+Van+Gool%2C+C%2E+K%2E+I%2E+Williams%2C+J%2E+Winn%2C+and+A%2E+Zisserman%2E+The+PASCAL+Visual+Object+Classes+%28VOC%29+Challenge%2E+IJCV%2C+2010%2E+1%2C+4)
16. C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. TPAMI, 2013. 10 [find](https://scholar.google.com/scholar?q=C%2E+Farabet%2C+C%2E+Couprie%2C+L%2E+Najman%2C+and+Y%2E+LeCun%2E+Learning+hierarchical+features+for+scene+labeling%2E+TPAMI%2C+2013%2E+10)
17. P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. TPAMI, 2010. 2, 4, 7, 12 [find](https://scholar.google.com/scholar?q=P%2E+Felzenszwalb%2C+R%2E+Girshick%2C+D%2E+McAllester%2C+and+D%2E+Ramanan%2E+Object+detection+with+discriminatively+trained+part+based+models%2E+TPAMI%2C+2010%2E+2%2C+4%2C+7%2C+12)
18. S. Fidler, R. Mottaghi, A. Yuille, and R. Urtasun. Bottom-up segmentation for top-down detection. In CVPR, 2013. 4, 5 [find](https://scholar.google.com/scholar?q=S%2E+Fidler%2C+R%2E+Mottaghi%2C+A%2E+Yuille%2C+and+R%2E+Urtasun%2E+Bottom%2Dup+segmentation+for+top%2Ddown+detection%2E+In+CVPR%2C+2013%2E+4%2C+5)
19. K. Fukushima. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 36(4):193–202, 1980. 1 [find](https://scholar.google.com/scholar?q=K%2E+Fukushima%2E+Neocognitron%3A+A+self%2Dorganizing+neural+network+model+for+a+mechanism+of+pattern+recognition+unaffected+by+shift+in+position%2E+Biological+cybernetics%2C+36%284%29%3A193%E2%80%93202%2C+1980%2E+1)
20. R. Girshick, P. Felzenszwalb, and D. McAllester. Discriminatively trained deformable part models, release 5. [http://www.cs.berkeley.edu/˜rbg/latent-v5/](http://www.cs.berkeley.edu/˜rbg/latent-v5/). 2, 5, 6, 7 [↗](http://www.cs.berkeley.edu/˜rbg/latent-v5/)
21. C. Gu, J. J. Lim, P. Arbeláez, and J. Malik. Recognition using regions. In CVPR, 2009. 2 [find](https://scholar.google.com/scholar?q=C%2E+Gu%2C+J%2E+J%2E+Lim%2C+P%2E+Arbela%CC%81ez%2C+and+J%2E+Malik%2E+Recognition+using+regions%2E+In+CVPR%2C+2009%2E+2)
22. B. Hariharan, P. Arbeláez, L. Bourdev, S. Maji, and J. Malik. Semantic contours from inverse detectors. In ICCV, 2011. 10 [find](https://scholar.google.com/scholar?q=B%2E+Hariharan%2C+P%2E+Arbela%CC%81ez%2C+L%2E+Bourdev%2C+S%2E+Maji%2C+and+J%2E+Malik%2E+Semantic+contours+from+inverse+detectors%2E+In+ICCV%2C+2011%2E+10)
23. D. Hoiem, Y. Chodpathumwan, and Q. Dai. Diagnosing error in object detectors. In ECCV. 2012. 2, 7, 8 [find](https://scholar.google.com/scholar?q=D%2E+Hoiem%2C+Y%2E+Chodpathumwan%2C+and+Q%2E+Dai%2E+Diagnosing+error+in+object+detectors%2E+In+ECCV%2E+2012%2E+2%2C+7%2C+8)
24. Y. Jia. Caffe: An open source convolutional architecture for fast feature embedding. [http://caffe.berkeleyvision.org/](http://caffe.berkeleyvision.org/), 2013. 3 [↗](http://caffe.berkeleyvision.org/)
25. A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012. 1, 3, 4, 7 [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+Hinton%2E+ImageNet+classification+with+deep+convolutional+neural+networks%2E+In+NIPS%2C+2012%2E+1%2C+3%2C+4%2C+7)
26. Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel. Backpropagation applied to handwritten zip code recognition. Neural Comp., 1989. 1 [find](https://scholar.google.com/scholar?q=Y%2E+LeCun%2C+B%2E+Boser%2C+J%2E+Denker%2C+D%2E+Henderson%2C+R%2E+Howard%2C+W%2E+Hubbard%2C+and+L%2E+Jackel%2E+Backpropagation+applied+to+handwritten+zip+code+recognition%2E+Neural+Comp%2E%2C+1989%2E+1)
27. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proc. of the IEEE, 1998. 1 [find](https://scholar.google.com/scholar?q=Y%2E+LeCun%2C+L%2E+Bottou%2C+Y%2E+Bengio%2C+and+P%2E+Haffner%2E+Gradient%2Dbased+learning+applied+to+document+recognition%2E+Proc%2E+of+the+IEEE%2C+1998%2E+1)
28. J. J. Lim, C. L. Zitnick, and P. Dollár. Sketch tokens: A learned mid-level representation for contour and object detection. In CVPR, 2013. 6, 7 [find](https://scholar.google.com/scholar?q=J%2E+J%2E+Lim%2C+C%2E+L%2E+Zitnick%2C+and+P%2E+Dolla%CC%81r%2E+Sketch+tokens%3A+A+learned+mid%2Dlevel+representation+for+contour+and+object+detection%2E+In+CVPR%2C+2013%2E+6%2C+7)