cvpr cvpr2013 cvpr2013-403 cvpr2013-403-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Bin Zhao, Eric P. Xing
Abstract: Many vision tasks require a multi-class classifier to discriminate multiple categories, on the order of hundreds or thousands. In this paper, we propose sparse output coding, a principled way for large-scale multi-class classification, by turning high-cardinality multi-class categorization into a bit-by-bit decoding problem. Specifically, sparse output coding is composed of two steps: efficient coding matrix learning with scalability to thousands of classes, and probabilistic decoding. Empirical results on object recognition and scene classification demonstrate the effectiveness ofour proposed approach.
[1] E. Allwein, R. Schapire, and Y. Singer. Reducing multiclass to binary: a unifying approach for margin classifiers. JMLR, 1:113–141, 2001. 1, 7
[2] S. Bengio, J. Weston, and D. Grangier. Label embedding trees for large multi-class tasks. In NIPS, 2010. 1, 3
[3] O. Boiman, E. Shechtman, and M. Irani. In defense of nearestneighbor based image classification. In CVPR, 2008. 1
[4] L. Bottou. Large-scale machine learning with stochastic gradient descent. In COMPSTAT, 2010. 7
[5] A. Budanitsky and G. Hirst. Evaluating wordnet-based measures of lexical semantic relatedness. Comput. Linguist., 32: 13–47, 2006. 3
[6] L. Cai and T. Hofmann. Hierarchical document categorization with support vector machines. In CIKM, 2004. 3
[7] P. Cheung and J. Kwok. A regularization framework for multipleinstance learning. In ICML, 2006. 4
[8] K. Crammer and Y. Singer. On the learnability and design of output codes for multiclass problems. Machine Learning, 2:265–292, 2002. 1, 2, 3
[9] O. Dekel, J. Keshet, and Y. Singer. Large margin hierarchical classi-
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22] fication. In ICML, 2004. 7 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. 1, 3, 6 J. Deng, S. Satheesh, A. Berg, and L. Fei-Fei. Fast and balanced: Efficient label tree learning for large scale object recognition. In NIPS, 2011. 1 S. Escalera, O. Pujol, and P. Radeva. On the decoding process in ternary error-correcting output codes. PAMI, 32(1): 120–134, 2010. 2 T. Gao and D. Koller. Multiclass boosting with hinge loss based on output coding. In ICML, 2011. 1, 2 D. Haussler. Convolution kernels on discrete structures. Technical report, 1999. 3 R. Jenatton, J. Mairal, G. Obozinski, and F. Bach. Proximal methods for hierarchical sparse coding. JMLR, 12:2297–2334, 2011. 4 A. Kosmopoulos, E. Gaussier, G. Paliouras, and S. Aseervatham. The ecir 2010 large scale hierarchical classification workshop. SIGIR Forum, 44(1):23–32, 2010. 7 S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, 2006. 6 Q. Le, M. Ranzato, R. Monga, M. Devin, K. Chen, G. Corrado, J. Dean, and A. Ng. Building high-level features using large scale unsupervised learning. In ICML, 2012. 1 Y. Lin, F. Lv, S. Zhu, M. Yang, T. Cour, K. Yu, L. Cao, and T. Huang. Large-scale image classification: fast feature extraction and svm training. In CVPR, 2011. 1 M. Parsana, S. Bhattacharya, C. Bhattacharyya, and K. Ramakrishnan. Kernels on attributed pointsets with applications. In NIPS, 2007. 3 B. P ´oczos, L. Xiong, and J. Schneider. Nonparametric divergence estimation with applications to machine learning on distributions. In UAI, 2011. 3 R. Rifkin and A. Klautau. In defense of one-vs-all classification. JMLR, 5: 101–141, 2004. 1
[23] R. Schapire. Using output codes to boost multiclass learing problems. In ICML, 1997. 1, 2
[24] A. J. Smola, S. Vishwanathan, and T. Hofmann. Kernel methods for missing variables. In AISTATS, 2005. 4
[25] J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong. Localityconstrained linear coding for image classification. In CVPR, 2010. 6
[26] J. Xiao, J. Hays, K. Ehinger, A. Oliva, and A. Torralba. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR, 2010. 1, 6
[27] X. Zhang, L. Liang, and H. Shum. Spectral error correcting output codes for efficient multiclass recognition. In ICCV, 2009. 7
[28] B. Zhao, F. Wang, and C. Zhang. Efficient multi-class maximum margin clustering. In ICML, 2008. 4
[29] X. Zhu, Z. Ghahramani, and J. Lafferty. Semi-supervised learning using gaussian fields and harmonic functions. In ICML, 2003. 5, 6 333333555755