In this paper we present a new model of semantic features that, unlike previously presented methods, does not rely on the presence of a labeled training data base, as the creation of the feature extraction function is done in an unsupervised manner.
We test these features on an unsupervised classification (clustering) task, and show that they outperform primitive (low-level) features, and that have performance comparable to that of supervised semantic features, which are much more expensive to determine relying on the presence of a labeled training set to train the feature extraction function.
KeywordsFeature Vector Semantic Feature Multiple Kernel Learning Sift Descriptor Primitive Feature
- 1.Bosch, A., Zisserman, A., Munoz, X.: Image classification using rois and multiple kernel learning. International Journal of Computer Vision 2008, 1–25 (2008)Google Scholar
- 4.Ciocca, G., Cusano, C., Santini, S., Schettini, R.: Supervised features for unsupervised image categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence (submitted, 2012)Google Scholar
- 5.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893 (2005)Google Scholar
- 8.Gehler, P., Nowozin, S.: On feature combination for multiclass object classification. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 221–228 (2009)Google Scholar
- 9.Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up 24(3), 577–584 (2005)Google Scholar
- 10.Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178 (2006)Google Scholar
- 11.Li, L.J., Fei-Fei, L.: What, where and who? classifying events by scene and object recognition. In: Proc. IEEE Int’l Conf. Computer Vision, pp. 1–8 (2007)Google Scholar
- 12.Li, L.J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: A high-level image representation for scene classification and semantic feature sparsification. In: Advances in Neural Information Processing Systems (2010)Google Scholar