Advertisement

A Least Squares Approach to Region Selection

  • Liantao Wang
  • Yan Liu
  • Jianfeng Lu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11305)

Abstract

Region selection is able to boost the recognition performance for images with background clutter by discovering the object regions. In this paper, we propose a region selection method under the least squares framework. With the assumption that an object is a combination of several over-segmented regions, we impose a selection variable on each region, and employ a linear model to perform classification. The model parameter and the selection parameter are alternatively updated to minimize a sum-of-squares error function. During the iteration, the selection parameter can automatically pick the discriminant regions accounting for the object category, then fine tunes the linear model with the objects, independently of the background. As a result, the learnt model is able to distinguish object regions and non-object regions, which actually generates irregular-shape object localization. Our method performs significantly better than the baselines on two datasets, and the performance can be further improved when combining deep CNN features. Moreover, the algorithm is easy to implement and computationally efficient because of the merits inherited from the least squares.

Keywords

Least squares Region selection Object localization 

Notes

Acknowledgment

This work was supported in part by the National Natural Science Foundation of China (NSFC) (No. 61703139), the Fundamental Research Funds for the Central Universities (No. 2016B12914), and the State Key Laboratory for Novel Software Technology (Nanjing University) (No. KFKT2017B09).

References

  1. 1.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: Advances in Neural Information Processing Systems, pp. 561–568 (2002)Google Scholar
  2. 2.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  3. 3.
    Behmo, R., Marcombes, P., Dalalyan, A., Prinet, V.: Towards optimal naive bayes nearest neighbor. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 171–184. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15561-1_13CrossRefGoogle Scholar
  4. 4.
    Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: British Machine Vision Conference, BMVC 2014, Nottingham, UK, 1–5 September 2014 (2014)Google Scholar
  5. 5.
    Chen, Q., Song, Z., Dong, J., Huang, Z., Hua, Y., Yan, S.: Contextualizing object detection and classification. IEEE Trans. Pattern Anal. Mach. Intell. 37(1), 13–27 (2015)CrossRefGoogle Scholar
  6. 6.
    Deselaers, T., Alexe, B., Ferrari, V.: Localizing objects while learning their appearance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 452–466. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15561-1_33CrossRefGoogle Scholar
  7. 7.
    Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915–1929 (2013)CrossRefGoogle Scholar
  8. 8.
    Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297–312. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10584-0_20CrossRefGoogle Scholar
  9. 9.
    Hariharan, B., Arbeláez, P.A., Girshick, R.B., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7–12 June 2015, pp. 447–456 (2015)Google Scholar
  10. 10.
    Harzallah, H., Jurie, F., Schmid, C.: Combining efficient object localization and image classification. In: IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, 27 September–4 October 2009, pp. 237–244 (2009)Google Scholar
  11. 11.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Beyond sliding windows: object localization by efficient subwindow search. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  12. 12.
    Li, Y.-F., Kwok, J.T., Tsang, I.W., Zhou, Z.-H.: A convex method for locating regions of interest with multi-instance learning. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS (LNAI), vol. 5782, pp. 15–30. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-04174-7_2CrossRefGoogle Scholar
  13. 13.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Ma, C., Huang, J., Yang, X., Yang, M.: Hierarchical convolutional features for visual tracking. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7–13 December 2015, pp. 3074–3082 (2015)Google Scholar
  15. 15.
    Nguyen, M.H., Torresani, L., de la Torre, L., Rother, C.: Weakly supervised discriminative localization and classification: a joint learning process. In: IEEE International Conference on Computer Vision, pp. 1925–1932 (2009)Google Scholar
  16. 16.
    Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based models. In: IEEE International Conference on Computer Vision, pp. 1307–1314 (2011)Google Scholar
  17. 17.
    Russakovsky, O., Lin, Y., Yu, K., Fei-Fei, L.: Object-centric spatial pooling for image classification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 1–15. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33709-3_1CrossRefGoogle Scholar
  18. 18.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  19. 19.
    Tang, K.D., Sukthankar, R., Yagnik, J., Li, F.F.: Discriminative segment annotation in weakly labeled video. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2483–2490 (2013)Google Scholar
  20. 20.
    Vijayanarasimhan, S., Grauman, K.: Efficient region search for object detection. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1401–1408 (2011)Google Scholar
  21. 21.
    Viola, P.A., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: Advances in Neural Information Processing Systems, pp. 1–8 (2005)Google Scholar
  22. 22.
    Wang, L., Meng, D., Hu, X., Lu, J., Zhao, J.: Instance annotation via optimal bow for weakly supervised object localization. IEEE Trans. Cybern. 47, 1313–1324 (2017)CrossRefGoogle Scholar
  23. 23.
    Wu, J., Yu, Y., Huang, C., Yu, K.: Deep multiple instance learning for image classification and auto-annotation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7–12 June 2015, pp. 3460–3469 (2015)Google Scholar
  24. 24.
    Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33783-3_45CrossRefGoogle Scholar
  25. 25.
    Yakhnenko, O., Verbeek, J., Schmid, C.: Region-based image classification with a latent SVM model. INRIA Technical report, pp. 1–13 (2011)Google Scholar
  26. 26.
    Zhao, J., Wang, L., Cabral, R., la Torre, F.D.: Feature and region selection for visual learning. IEEE Trans. Image Process. 25, 1084–1094 (2016)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of IoT EngineeringHohai UniversityChangzhouChina
  2. 2.State Key Laboratory for Novel Software TechnologyNanjing UniversityNanjingChina
  3. 3.School of Computer ScienceNanjing University of Science and TechnologyNanjingChina

Personalised recommendations