Advertisement

R-CNN for Small Object Detection

  • Chenyi ChenEmail author
  • Ming-Yu Liu
  • Oncel Tuzel
  • Jianxiong Xiao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10115)

Abstract

Existing object detection literature focuses on detecting a big object covering a large part of an image. The problem of detecting a small object covering a small part of an image is largely ignored. As a result, the state-of-the-art object detection algorithm renders unsatisfactory performance as applied to detect small objects in images. In this paper, we dedicate an effort to bridge the gap. We first compose a benchmark dataset tailored for the small object detection problem to better evaluate the small object detection performance. We then augment the state-of-the-art R-CNN algorithm with a context model and a small region proposal generator to improve the small object detection performance. We conduct extensive experimental validations for studying various design choices. Experiment results show that the augmented R-CNN algorithm improves the mean average precision by 29.8% over the original R-CNN algorithm on detecting small objects.

Keywords

Object Detection Average Precision Small Object Convolutional Neural Network Object Instance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Supplementary material

440742_1_En_14_MOESM1_ESM.pdf (1.8 mb)
Supplementary material 1 (pdf 1841 KB)

References

  1. 1.
    Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) challenge. Int. J. Comput. Vis. 88, 303–338 (2010)CrossRefGoogle Scholar
  2. 2.
    Torralba, A., Efros, A., et al.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521–1528 (2011)Google Scholar
  3. 3.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587 (2014)Google Scholar
  4. 4.
    Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  5. 5.
    Kembhavi, A., Harwood, D., Davis, L.S.: Vehicle detection using partial least squares. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1250–1265 (2011)CrossRefGoogle Scholar
  6. 6.
    Morariu, V., Ahmed, E., Santhanam, V., Harwood, D., Davis, L.S., et al.: Composite discriminant factor analysis. In: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 564–571 (2014)Google Scholar
  7. 7.
    Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 340–353. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33712-3_25 CrossRefGoogle Scholar
  8. 8.
    Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10602-1_48 Google Scholar
  9. 9.
    Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: exploring a large collection of scene categories. Int. J. Comput. Vis. 119, 1–20 (2014)MathSciNetGoogle Scholar
  10. 10.
    Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154–171 (2013)CrossRefGoogle Scholar
  11. 11.
    Zitnick, C.L., Dollár, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391–405. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10602-1_26 Google Scholar
  12. 12.
    Kuo, W., Hariharan, B., Malik, J.: DeepBox: learning objectness with convolutional networks. arXiv preprint arXiv:1505.02146 (2015)
  13. 13.
    Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2155–2162 (2014)Google Scholar
  14. 14.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  15. 15.
    Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A., Hebert, M., et al.: An empirical study of context in object detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1271–1278 (2009)Google Scholar
  16. 16.
    Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M., et al.: Context-based vision system for place and object recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 273–280 (2003)Google Scholar
  17. 17.
    Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. arXiv preprint arXiv:1505.01197 (2015)
  18. 18.
    Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. arXiv preprint arXiv:1505.01749 (2015)
  19. 19.
    Zhu, Y., Urtasun, R., Salakhutdinov, R., Fidler, S.: segDeepM: exploiting segmentation and context in deep neural networks for object detection. arXiv preprint arXiv:1502.04275 (2015)
  20. 20.
    Mottaghi, R., Chen, X., Liu, X., Cho, N.G., Lee, S.W., Fidler, S., Urtasun, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 891–898 (2014)Google Scholar
  21. 21.
    Zhang, Y., Sohn, K., Villegas, R., Pan, G., Lee, H.: Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction. arXiv preprint arXiv:1504.03293 (2015)
  22. 22.
    Yoo, D., Park, S., Lee, J.Y., Paek, A., Kweon, I.S.: AttentionNet: aggregating weak directions for accurate object detection. arXiv preprint arXiv:1506.07704 (2015)
  23. 23.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv preprint arXiv:1506.02640 (2015)
  24. 24.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.: SSD: single shot multibox detector. arXiv preprint arXiv:1512.02325 (2015)
  25. 25.
    Pepik, B., Benenson, R., Ritschel, T., Schiele, B.: What is holding back convnets for detection? In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 517–528. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24947-6_43 CrossRefGoogle Scholar
  26. 26.
    Liu, M.Y., Mallya, A., Tuzel, O., Chen, X.: Unsupervised network pretraining via encoding human design. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9. IEEE (2016)Google Scholar
  27. 27.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  28. 28.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627–1645 (2010)CrossRefGoogle Scholar
  29. 29.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Chenyi Chen
    • 1
    Email author
  • Ming-Yu Liu
    • 2
  • Oncel Tuzel
    • 2
  • Jianxiong Xiao
    • 1
  1. 1.Princeton UniversityPrincetonUSA
  2. 2.Mitsubishi Electric Research Labs (MERL)CambridgeUSA

Personalised recommendations