Advertisement

ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

  • Vadim Kantorov
  • Maxime Oquab
  • Minsu Cho
  • Ivan LaptevEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9909)

Abstract

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by introducing two types of context-aware guidance models, additive and contrastive models, that leverage their surrounding context regions to improve localization. The additive model encourages the predicted object region to be supported by its surrounding context region. The contrastive model encourages the predicted object region to be outstanding from its surrounding context region. Our approach benefits from the recent success of convolutional neural networks for object recognition and extends Fast R-CNN to weakly supervised object localization. Extensive experimental evaluation on the PASCAL VOC 2007 and 2012 benchmarks shows that our context-aware approach significantly improves weakly supervised localization and detection.

Keywords

Object recognition Object detection Weakly supervised object localization Context Convolutional neural networks 

Notes

Acknowledgments

We thank Hakan Bilen, Relja Arandjelović, and Soumith Chintala for fruitful discussion and help. This work was supported by the ERC grants VideoWorld and Activia, and the MSR-INRIA laboratory.

Supplementary material

419978_1_En_22_MOESM1_ESM.pdf (2.1 mb)
Supplementary material 1 (pdf 2152 KB)

References

  1. 1.
    Wang, C., Ren, W., Huang, K., Tan, T.: Weakly supervised object localization with latent category learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 431–445. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10599-4_28 Google Scholar
  2. 2.
    Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. arXiv preprint (2015). arXiv:1503.00949
  3. 3.
    LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRefGoogle Scholar
  4. 4.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  5. 5.
    Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free?-weakly-supervised learning with convolutional neural networks. In: CVPR, pp. 685–694 (2015)Google Scholar
  6. 6.
    Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: CVPR (2016)Google Scholar
  7. 7.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. PAMI 38(1), 142–158 (2016)CrossRefGoogle Scholar
  8. 8.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)Google Scholar
  9. 9.
    Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV, pp. 1134–1142 (2015)Google Scholar
  10. 10.
    Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: ICCV, pp. 273–280. IEEE (2003)Google Scholar
  11. 11.
    Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: ICCV, pp. 1–8. IEEE (2007)Google Scholar
  12. 12.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. PAMI 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  13. 13.
    Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for multi-class object layout. In: ICCV, pp. 229–236, September 2009Google Scholar
  14. 14.
    Chum, O., Zisserman, A.: An exemplar model for learning object classes. In: CVPR, pp. 1–8. IEEE (2007)Google Scholar
  15. 15.
    Shi, Z., Siva, P., Xiang, T., Mary, Q.: Transfer learning by ranking for weakly supervised object annotation. In: BMVC, vol. 2, p. 5. Citeseer (2012)Google Scholar
  16. 16.
    Siva, P., Russell, C., Xiang, T.: In defence of negative mining for annotating weakly labelled data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 594–608. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33712-3_43 Google Scholar
  17. 17.
    Deselaers, T., Alexe, B., Ferrari, V.: Weakly supervised localization and learning with generic knowledge. IJCV 100(3), 275–293 (2012)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Siva, P., Russell, C., Xiang, T., Agapito, L.: Looking beyond the image: unsupervised learning for object saliency and detection. In: CVPR, pp. 3238–3245 (2013)Google Scholar
  19. 19.
    Song, H.O., Girshick, R., Jegelka, S., Mairal, J., Harchaoui, Z., Darrell, T.: On learning to localize objects with minimal supervision. arXiv preprint (2014). arXiv:1403.1024
  20. 20.
    Song, H.O., Lee, Y.J., Jegelka, S., Darrell, T.: Weakly-supervised discovery of visual pattern configurations. In: NIPS (2014)Google Scholar
  21. 21.
    Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with posterior regularization. In: BMVC (2014)Google Scholar
  22. 22.
    Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with convex clustering. In: CVPR, pp. 1081–1089 (2015)Google Scholar
  23. 23.
    Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS, pp. 2008–2016 (2015)Google Scholar
  24. 24.
    Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. arXiv preprint (2015). arXiv:1512.04150
  25. 25.
    Long, P.M., Tan, L.: PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples. Mach. Learn. 30(1), 7–21 (1998)CrossRefzbMATHGoogle Scholar
  26. 26.
    Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. PAMI 34(11), 2189–2202 (2012)CrossRefGoogle Scholar
  27. 27.
    Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015)Google Scholar
  28. 28.
    Oliva, A., Torralba, A.: The role of context in object recognition. Trends in Cogn. Sci. 11(12), 520–527 (2007)CrossRefGoogle Scholar
  29. 29.
    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, vol. 7573, pp. 1–15. Springer, Heidelberg (2012)Google Scholar
  30. 30.
    Doersch, C., Gupta, A., Efros, A.A.: Context as supervisory signal: discovering objects with predictable context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 362–377. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10578-9_24 Google Scholar
  31. 31.
    Cho, M., Kwak, S., Schmid, C., Ponce, J.: Unsupervised object discovery and localization in the wild: part-based matching with bottom-up region proposals. In: CVPR, pp. 1201–1210 (2015)Google Scholar
  32. 32.
    Kwak, S., Cho, M., Laptev, I., Ponce, J., Schmid, C.: Unsupervised object discovery and tracking in video collections. In: ICCV, pp. 3173–3181 (2015)Google Scholar
  33. 33.
    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 (2014)Google Scholar
  34. 34.
    Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154–171 (2013)CrossRefGoogle Scholar
  35. 35.
    He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. PAMI 37(9), 1904–1916 (2015)CrossRefGoogle Scholar
  36. 36.
    Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
  37. 37.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC 2012) Results (2012). http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
  38. 38.
    Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: BigLearn, NIPS Workshop. Number EPFL-CONF-192376 (2011)Google Scholar
  39. 39.
    Gidaris, S., Komodakis, N.: Locnet: Improving localization accuracy for object detection. arXiv preprint (2015). arXiv:1511.07763
  40. 40.
    Zagoruyko, S.: loadcaffe (2015). https://github.com/szagoruyko/loadcaffe
  41. 41.
    Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E.: cuDNN: efficient primitives for deep learning. arXiv preprint (2014). arXiv:1410.0759
  42. 42.

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Vadim Kantorov
    • 1
  • Maxime Oquab
    • 1
  • Minsu Cho
    • 1
  • Ivan Laptev
    • 1
    Email author
  1. 1.WILLOW project team, Inria / ENS / CNRSParisFrance

Personalised recommendations