Proceedings

Deep Descriptor Transforming for Image Co-Localization

Download BibTeX Cite

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Main track. Pages 3048-3054.

https://doi.org/10.24963/ijcai.2017/425

© 2017 International Joint Conferences on Artificial Intelligence

Abstract

Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of images. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark image co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data.

  1. [Bilen et al., 2015] H. Bilen, M. Pedersoli, and T. Tuytelaars. Weakly supervised object detection with convex clustering. In CVPR, pages 1081-1089, 2015.
  2. [Chen et al., 2013] M. Chen, W. Li, W. Zhang, and X.-G. Wang. Dimensionality reduction with generalized linear models. In IJCAI, pages 1267-1272, 2013. IJCAI
  3. [Cho et al., 2015] M. Cho, S. Kwak, C. Schmid, and J. Ponce. Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals. In CVPR, pages 1201-1210, 2015.
  4. [Cinbis et al., 2015] R. G. Cinbis, J. J. Verbeek, and C. Schmid. Multi-fold MIL training for weakly supervised object localization. In CVPR, pages 2409-2416, 2015.
  5. [Davidson, 2009] I. Davidson. Knowledge driven dimension reduction for clustering. In IJCAI, pages 1034-1039, 2009. IJCAI
  6. [Everingham et al., 2015] M. Everingham, S. M. Ali Eslami, L. Van Gool, C. K. L. Williams, J. Winn, and A. Zisser- man. The PASCAL visual object classes challenge: A retrospective. IJCV, 111(1):98-136, 2015.
  7. [Ghodrati et al., 2015] A. Ghodrati, A. Diba, M. Pedersoli, T. Tuytelaars, and L. Van Gool. Deepproposal: Hunting objects by cascading deep convolutional layers. In ICCV, pages 2578-2586, 2015.
  8. [Gu et al., 2011] Q.-Q. Gu, Z.-H. Li, and J.-W. Han. Joint feature selection and subspace learning. In IJCAI, pages 1294-1299, 2011. IJCAI
  9. [Joulin et al., 2010] A. Joulin, F. Bach, and J. Ponce. Dis- criminative clustering for image co-segmentation. In ICCV, pages 2984-2991, 2010.
  10. [Joulin et al., 2012] A. Joulin, F. Bach, and J. Ponce. Multi- class co-segmentation. In ICCV, pages 139-150, 2012.
  11. [Joulin et al., 2014] A. Joulin, K. Tang, and L. Fei-Fei. Ef- ficient image and video co-localization with Frank-Wolfe algorithm. In ECCV, pages 253-268, 2014.
  12. [Kim et al., 2011] G. Kim, E. P. Xing, L. Fei-Fei, and T. Kanade. Distributed co-segmentation via submodular optimization on anisotropic diffusion. In ICCV, pages 169- 176, 2011.
  13. [Li et al., 2016] Y. Li, L. Liu, C. Shen, and A. V. D. Hengel. Image co-localization by mimicking a good detector's con- fidence score distribution. In ECCV, pages 19-34, 2016.
  14. [Nie et al., 2011] F.-P. Nie, H. Huang, C. Ding, D.-J. Luo, and H. Wang. Robust principal component analysis with non-greedy ℓ 1 -norm maximization. In IJCAI, pages 1433- 1438, 2011.
  15. K. Pearson. On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2(11):559-572, 1901.
  16. [Ren et al., 2016] W. Ren, K. Huang, D. Tao, and T. Tan. Weakly supervised large scale object localization with mul- tiple instance learning and bag splitting. IEEE TPAMI, 38(2):405-416, 2016.
  17. [Rubinstein et al., 2013] M. Rubinstein, A. Joulin, J. Kopf, and C. Liu. Unsupervised joint object discovery and seg- mentation in internet images. In CVPR, pages 1939-1946, 2013.
  18. [Russakovsky et al., 2015] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei. Im- ageNet large scale visual recognition challenge. IJCV, 115(3):211-252, 2015.
  19. [Shi et al., 2013] Z. Shi, T. M. Hospedales, and T. Xiang. Bayesian joint topic modelling for weakly supervised object localisation. In ICCV, pages 2984-2991, 2013.
  20. [Simonyan and Zisserman, 2015] K. Simonyan and A. Zis- serman. Very deep convolutional networks for large-scale image recognition. In ICLR, pages 1-14, 2015.
  21. [Siva and Xiang, 2011] P. Siva and T. Xiang. Weakly super- vised object detector learning with model drift detection. In CVPR, pages 343-350, 2011.
  22. [Tang et al., 2014] K. Tang, A. Joulin, L. Li, and L. Fei-Fei. Co-localization in real-world images. In CVPR, pages 1464-1471, 2014.
  23. [Vedaldi and Lenc, 2015] A. Vedaldi and K. Lenc. MatCon- vNet -convolutional neural networks for MATLAB. In ACM MM, pages 689-692, 2015.
  24. [Wang et al., 2014] C. Wang, W. Ren, K. Huang, and T. Tan. Weakly supervised object localization with latent category learning. In ECCV, pages 431-445, 2014.
  25. [Wang et al., 2015] X. Wang, Z. Zhu, C. Yao, and X. Bai. Relaxed multiple-instance SVM with application to object discovery. In ICCV, pages 1224-1232, 2015.
  26. [Wei et al., 2017] X.-S. Wei, J.-H. Luo, J. Wu, and Z.-H. Zhou. Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE TIP, 26(6):2868-2881, 2017.
  27. [Yang et al., 2017] Y. Yang, D.-C. Zhan, Y. Fan, Y. Jiang, and Z.-H. Zhou. Deep learning for fixed model reuse. In AAAI, pages 2831-2837, 2017.
  28. [Zhang et al., 2009] T. Zhang, D. Tao, X. Li, and J. Yang. Patch alignment for dimensionality reduction. IEEE TKDE, 21(9):1299-1313, 2009.
  29. [Zhang et al., 2013] L. Zhang, L. Zhang, D. Tao, and X. Huang. Tensor discriminative locality alignment for hy- perspectral image spectral-spatial feature extraction. IEEE TGRS, 51(1):242-256, 2013.
  30. [Zhang et al., 2016] D. Zhang, D. Meng, L. Zhao, and J. Han. Bridging saliency detection to weakly supervised object detection based on self-paced curriculum. In IJCAI, pages 3538-3544, 2016.
  31. [Zhao and Fu, 2015] H. Zhao and Y. Fu. Semantic single video segmentation with robust graph representation. In IJCAI, pages 2219-2225, 2015. IJCAI
  32. [Zhou, 2016] Z.-H. Zhou. Learnware: On the future of ma- chine learning. Frontiers of Computer Science, 10(4):589- 590, 2016.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards