iccv iccv2013 iccv2013-142 iccv2013-142-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Dengxin Dai, Luc Van_Gool
Abstract: This paper investigates the problem of semi-supervised classification. Unlike previous methods to regularize classifying boundaries with unlabeled data, our method learns a new image representation from all available data (labeled and unlabeled) andperformsplain supervised learning with the new feature. In particular, an ensemble of image prototype sets are sampled automatically from the available data, to represent a rich set of visual categories/attributes. Discriminative functions are then learned on these prototype sets, and image are represented by the concatenation of their projected values onto the prototypes (similarities to them) for further classification. Experiments on four standard datasets show three interesting phenomena: (1) our method consistently outperforms previous methods for semi-supervised image classification; (2) our method lets itself combine well with these methods; and (3) our method works well for self-taught image classification where unlabeled data are not coming from the same distribution as la- beled ones, but rather from a random collection of images.
[1] M. Belkin, P. Niyogi, and V. Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. JMLR, 7(36):2399–2434, 2006.
[2] K. P. Bennett and A. Demiriz. Semi-supervised support vector machines. In NIPS, 1998.
[3] A. Bosch, A. Zisserman, and X. Muoz. Image classification using random forests and ferns. In ICCV, 2007.
[4] C.-C. Chang and C.-J. Lin. LIBSVM: A library for support
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15] vector machines. ACM Transactions on Intelligent Systems and Technology, 2: 1–27, 2011. D. Dai, M. Prasad, C. Leistner, and L. V. Gool. Ensemble partitioning for unsupervised image categorization. In ECCV, 2012. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR, 2009. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. Liblinear: A library for large linear classification. J. Mach. Learn. Res., 9: 1871–1874, 2008. A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth. Describing objects by their attributes. In CVPR, 2009. L. Fei-Fei, R. Fergus, and P. Perona. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In CVPR, WS, 2004. R. Fergus, Y. Weiss, and A. Torralba. Semi-supervised learning in gigantic image collections. In NIPS, 2009. M. Guillaumin, J. J. Verbeek, and C. Schmid. Multimodal semi-supervised learning for image classification. In CVPR, 2010. P. Jain and A. Kapoor. Active learning for large multi-class problems. In CVPR, 2009. T. Joachims. Transductive inference for text classification using support vector machines. In ICML, 1999. T. Kozakaya, S. Ito, and S. Kubota. Random ensemble metrics for object recognition. In ICCV, 2011. P. Kumar Mallapragada, R. Jin, A. Jain, and Y. Liu. Semiboost: Boosting for semi-supervised learning. TPAMI, 31(1 1):2000–2014, 2009.
[16] S. Lazebnik, C. Schmid, and J. Ponce. A sparse texture representation using local affine regions. TPAMI, 27(8): 1265– 1278, 2005.
[17] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, 2006.
[18] C. Leistner, A. Saffari, J. Santner, and H. Bischof. Semisupervised random forests. In ICCV, 2009.
[19] L.-J. Li, H. Su, E. P. Xing, and F.-F. Li. Object bank: A highlevel image representation for scene classification & semantic feature sparsification. In NIPS, 2010.
[20] Y.-F. Li and Z.-H. Zhou. Towards making unlabeled data never hurt. In ICML, 2011.
[21] X. Liu, X. Yuan, S. Yan, and H. Jin. Multi-class semisupervised svms with positiveness exclusive regularization. In ICCV, 2011.
[22] T. Ojala, M. Pietik¨ ainen, and T. Ma¨ enp a¨ a¨. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. TPAMI, 24(7):971–987, 2002.
[23] A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3): 145–175, 2001.
[24] A. Quattoni, M. Collins, and T. Darrell. Transfer learning for image classification with sparse prototype representations. In CVPR, 2008.
[25] R. Raina, A. Battle, H. Lee, B. Packer, and A. Y. Ng. Selftaught learning: transfer learning from unlabeled data. In ICML, 2007.
[26] L. Rokach. Ensemble-based classifiers. Artificial Intelligence Review, 33(1-2): 1–39, 2010.
[27] E. Rosch. Principles of categorization. Cognition and Cate-
[28]
[29]
[30] [3 1]
[32]
[33]
[34]
[35] gorization, pages 27–48, 1978. V. Sharmanska, N. Quadrianto, and C. Lampert. Augmented attribute representations. In ECCV. 2012. A. Shrivastava, S. Singh, and A. Gupta. Constrained semisupervised learning using attributes and comparative attributes. In ECCV, 2012. L. Torresani, M. Szummer, and A. Fitzgibbon. Efficient object category recognition using classemes. In ECCV, 2010. Y. Yang and S. Newsam. Bag-of-visual-words and spatial extensions for land-use classification. In ACM GIS, 2010. F. X. Yu, L. Cao, R. S. Feris, J. R. Smith, and S.-F. Chang. Designing category-level attributes for discriminative visual recognition. In CVPR, 2013. D. Zhou, O. Bousquet, T. N. Lal, J. Weston, and B. Schlkopf. Learning with local and global consistency. In NIPS, 2004. X. Zhu, Z. Ghahramani, and J. Lafferty. Semi-supervised learning using gaussian fields and harmonic functions. In ICML, 2003. X. Zhu and A. B. Goldberg. Introduction to Semi-Supervised Learning. 2009. 2079