iccv iccv2013 iccv2013-332 iccv2013-332-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Marc T. Law, Nicolas Thome, Matthieu Cord
Abstract: This paper introduces a novel similarity learning framework. Working with inequality constraints involving quadruplets of images, our approach aims at efficiently modeling similarity from rich or complex semantic label relationships. From these quadruplet-wise constraints, we propose a similarity learning framework relying on a convex optimization scheme. We then study how our metric learning scheme can exploit specific class relationships, such as class ranking (relative attributes), and class taxonomy. We show that classification using the learned metrics gets improved performance over state-of-the-art methods on several datasets. We also evaluate our approach in a new application to learn similarities between webpage screenshots in a fully unsupervised way.
[1] E. Adar, J. Teevan, and S. Dumais. Resonance on the web: web dynamics and revisitation patterns. In CHI, 2009.
[2] S. Avila, N. Thome, M. Cord, E. Valle, and A. d. A. Ara u´jo. Pooling in image representation: The visual codeword point of view. CVIU, 117(5):453–465, 2013.
[3] M. Ben Saad and S. Gan ¸carski. Archiving the Web using Page Changes Pattern: A Case Study. In JCDL, 2011.
[4] O. Chapelle. Training a support vector machine in the primal. Neural Computation, 19(5): 1155–1 178, 2007.
[5] O. Chapelle and S. S. Keerthi. Efficient algorithms for ranking with svms. Inf. Retrieval, 13(3):201–215, 2010.
[6] G. Chechik, V. Sharma, U. Shalit, and S. Bengio. Large scale online learning of image similarity through ranking. JMLR, 11: 1109–1 135, 2010.
[7] M. Cord and P. Cunningham. Machine learning techniques for multimedia. Springer, 2008.
[8] J. V. Davis, B. Kulis, P. Jain, S. Sra, and I. S. Dhillon. Information-theoretic metric learning. In ICML, 2007.
[9] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. FeiFei. Imagenet: A large-scale hierarchical image database. In CVPR, 2009.
[10] A. Frome, Y. Singer, F. Sha, and J. Malik. Learning globallyconsistent local distance functions for shape-based image retrieval and classification. In ICCV, 2007.
[11] H. Goh, N. Thome, M. Cord, and J. Lim. Unsupervised and supervised visual codes with restricted boltzmann machines.
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24] In ECCV, 2012. M. Guillaumin, J. Verbeek, and C. Schmid. Is that you? metric learning approaches for face identification. In ICCV, 2009. S. J. Hwang, K. Grauman, and F. Sha. Learning a tree of metrics with disjoint visual features. In NIPS, 2011. P. Jain, B. Kulis, and K. Grauman. Fast image search for learned metrics. In CVPR, 2008. M. Kumar, P. Torr, and A. Zisserman. An invariant large margin nearest neighbour classifier. In ICCV, 2007. N. Kumar, A. Berg, P. Belhumeur, and S. Nayar. Attribute and simile classifiers for face verification. In ICCV, 2009. T. Mensink, J. Verbeek, F. Perronnin, and G. Csurka. Metric learning for large-scale image classification: generalizing to new classes at near-zero cost. In ECCV, 2012. A. Mignon and F. Jurie. Pcca: A new approach for distance learning from sparse pairwise constraints. In CVPR, 2012. A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3): 145–175, 2001. D. Parikh and K. Grauman. Relative attributes. In ICCV, 2011. T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio. Robust object recognition with cortex-like mechanisms. PAMI, 29(3):41 1–426, 2007. J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV, 2003. R. Song, H. Liu, J. Wen, and W. Ma. Learning block importance models for web pages. In WWW, 2004. C. Theriault, N. Thome, and M. Cord. Extended coding and pooling in the hmax model. IEEE Transactions on Image
[25]
[26]
[27]
[28]
[29]
[30] Processing, 22(2):764–777, 2013. L. Torresani and K. Lee. Large margin component analysis. In NIPS, 2007. N. Verma, D. Mahajan, S. Sellamanickam, and V. Nair. Learning hierarchical similarity metrics. In CVPR, 2012. K. Weinberger and O. Chapelle. Large margin taxonomy embedding with an application to document categorization. In NIPS, 2008. K. Weinberger and L. Saul. Distance metric learning for large margin nearest neighbor classification. JMLR, 10:207– 244, 2009. E. Xing, A. Ng, M. Jordan, and S. Russell. Distance metric learning, with application to clustering with sideinformation. In NIPS, 2002. J. Yang, K. Yu, Y. Gong, and T. Huang. Linear spatial pyramid matching using sparse coding for image classification. In CVPR, 2009. 256