Elamur Research⌕
☰
home / papers / 2013 / OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Paper · 2013 · Pierre Sermanet, David Eigen, Xiang Zhang et al.

Summary

OverFeat addresses classification, localization and detection on ImageNet with one convolutional network that shares a common feature base, rather than separate pipelines. The authors train a Krizhevsky-style ConvNet on the ILSVRC 2012 training data (about 1.2M images, 1000 classes). Their changes include a smaller first-layer stride, non-overlapping pooling and no contrast normalization. At test time the network runs densely over the image at several scales, with fully connected layers treated as 1x1 convolutions, so sliding-window inference stays cheap. For localization, a regression head on the shared features predicts bounding-box coordinates at each window position. Box predictions are then merged and accumulated instead of being pruned by non-maximum suppression. Detection adds a background class, with negative examples mined per image during training instead of through separate bootstrapping rounds. The system won the ILSVRC 2013 localization task and performed strongly in detection and classification. It showed that dense sliding windows can compete with region-proposal methods. The authors also released the feature extractor publicly.

Key points

  • ILSVRC 2013 localization winner with 29.9% top-5 error. Using several scales mattered: one centered crop gave 40%, two scales 31.5%, and four scales 30.0%.
  • Detection placed 3rd in the competition with 19.4% mAP. After the competition it reached 24.3% mAP, beating the winning UvA result of 22.6%, mainly through longer training and multi-scale context.
  • Classification ranked 4th in ILSVRC 2013.
  • A single box regressor shared across all classes worked better than per-class regressors (31.3% vs 44.1% error), probably because there are few box annotations per class.
  • The released "OverFeat" feature extractor comes in fast and accurate model variants.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓New York UniversityNew York · United States219 works · 103,487 citations🎓Courant Institute of Mathematical SciencesNew York · United States8 works · 9,589 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksComputer Vision and Pattern Recognition · 3,486 works

Cite

Cite as Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and Yann LeCun. 2013. OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. arXiv:1312.6229.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.1312.6229 · arXiv 1312.6229

@misc{sermanet2013overfeat,
  title = {{OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks}},
  author = {Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and Yann LeCun},
  year = {2013},
  doi = {10.48550/arxiv.1312.6229},
  eprint = {1312.6229},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1312.6229}
}

References

30 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. J. Carreira, F. Li, and C. Sminchisescu. Object recognition by sequential figure-ground ranking. International journal of computer vision, 98(3):243–262, 2012. find
  2. J. Carreira and C. Sminchisescu. Constrained parametric min-cuts for automatic object segmentation, release 1. http://sminchisescu.ins.uni-bonn.de/code/cpmc/. ↗
  3. D. C. Ciresan, J. Meier, and J. Schmidhuber. Multi-column deep neural networks for image classification. In CVPR, 2012.
  4. M. Delakis and C. Garcia. Text detection with convolutional neural networks. In International Conference on Computer Vision Theory and Applications (VISAPP 2008), 2008. find
  5. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09, 2009. find
  6. I. Endres and D. Hoiem. Category independent object proposals. In Computer Vision–ECCV 2010, pages 575–588. Springer, 2010. find
  7. C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013. in press. find
  8. C. Garcia and M. Delakis. Convolutional face finder: A neural architecture for fast and robust face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004. find
  9. A. Giusti, D. C. Ciresan, J. Masci, L. M. Gambardella, and J. Schmidhuber. Fast image scanning with deep max-pooling convolutional neural networks. In International Conference on Image Processing (ICIP), 2013. find
  10. R. Hadsell, P. Sermanet, M. Scoffier, A. Erkan, K. Kavackuoglu, U. Muller, and Y. LeCun. Learning long-range vision for autonomous off-road driving. Journal of Field Robotics, 26(2):120–144, February 2009. find
  11. G. Hinton, N. Srivastave, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580, 2012. find
  12. G. E. Hinton, A. Krizhevsky, and S. D. Wang. Transforming auto-encoders. In Artificial Neural Networks and Machine Learning–ICANN 2011, pages 44–51. Springer Berlin Heidelberg, 2011. find
  13. V. Jain, J. F. Murray, F. Roth, S. Turaga, V. Zhigulin, K. Briggman, M. Helmstaedter, W. Denk, and H. S. Seung. Supervised learning of image restoration with convolutional networks. In ICCV’07. find
  14. K. Jarrett, K. Kavukcuoglu, M. Ranzato, and Y. LeCun. What is the best multi-stage architecture for object recognition? In Proc. International Conference on Computer Vision (ICCV’09). IEEE, 2009. find
  15. A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.
  16. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Handwritten digit recognition with a back-propagation network. In D. Touretzky, editor, Advances in Neural Information Processing Systems (NIPS 1989), volume 2, Denver, CO, 1990. Morgan Kaufman. find
  17. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, November 1998. find
  18. Y. LeCun, F.-J. Huang, and L. Bottou. Learning methods for generic object recognition with invariance to pose and lighting. In Proceedings of CVPR’04. IEEE Press, 2004. find
  19. S. Manen, M. Guillaumin, and L. Van Gool. Prime object proposals with randomized prims algorithm. In International Conference on Computer Vision (ICCV), 2013. find
  20. O. Matan, J. Bromley, C. Burges, J. Denker, L. Jackel, Y. LeCun, E. Pednault, W. Satterfield, C. Stenard, and T. Thompson. Reading handwritten digits: A zip code recognition system. IEEE Computer, 25(7):59– 63, July 1992. find
  21. F. Ning, D. Delhomme, Y. LeCun, F. Piano, L. Bottou, and P. Barbano. Toward automatic phenotyping of developing embryos from videos. IEEE Transactions on Image Processing, 14(9):1360–1371, September 2005. Special issue on Molecular and Cellular Bioimaging. find
  22. S. Nowlan and J. Platt. A convolutional neural network hand tracker. pages 901–908, San Mateo, CA, 1995. Morgan Kaufmann. find
  23. M. Osadchy, Y. LeCun, and M. Miller. Synergistic face detection and pose estimation with energy-based models. Journal of Machine Learning Research, 8:1197–1215, May 2007. find
  24. P. Sermanet, S. Chintala, and Y. LeCun. Convolutional neural networks applied to house numbers digit classification. In International Conference on Pattern Recognition (ICPR 2012), 2012. find
  25. P. Sermanet, K. Kavukcuoglu, S. Chintala, and Y. LeCun. Pedestrian detection with unsupervised multi-stage feature learning. In Proc. International Conference on Computer Vision and Pattern Recognition (CVPR’13). IEEE, June 2013. find
  26. P. Sermanet and Y. LeCun. Traffic sign recognition with multi-scale convolutional networks. In Proceedings of International Joint Conference on Neural Networks (IJCNN’11), 2011. find
  27. G. Taylor, R. Fergus, G. Williams, I. Spiro, and C. Bregler. Pose-sensitive embedding by nonlinear nca regression. In NIPS, 2011. find
  28. G. Taylor, I. Spiro, C. Bregler, and R. Fergus. Learning invarance through imitation. In CVPR, 2011. find
  29. J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. M. Smeulders. Selective search for object recognition. International Journal of Computer Vision, 104(2):154–171, 2013. find
  30. R. Vaillant, C. Monrocq, and Y. LeCun. Original approach for the localisation of objects in images. IEE Proc on Vision, Image, and Signal Processing, 141(4):245–250, August 1994. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sermanet-2013-overfeat-integrated-recognition-localization-detection/