Abstract
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns of visual co-occurrence and if the learned visual models improve performance when less labeled data are available. We present and discuss results that support these hypotheses. Probabilistic Latent Semantic Analysis (PLSA) automatically identifies aspects from the data with semantic meaning, producing unsupervised soft clustering. The resulting compact representation retains sufficient discriminative information for accurate object classification, and improves the classification accuracy through the use of unlabeled data when less labeled training data are available. We perform experiments on a 7-class object database containing 1776 images.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. ACM Press, New York (1999)
Blei, D., Andrew, Y., Jordan, M.: Latent dirichlet allocation. Journal of Machine Learning Research 3, 993–1020 (2003)
Buntine, W.: Variational extensions to em and multinomial pca. In: Proc. of Europ. Conf. on Machine Learning, Helsinki (August 2002)
Duygulu, P., Barnard, K., Freitas, N., Forsyth, D.: Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 97–112. Springer, Heidelberg (2002)
Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning 42, 177–196 (2001)
Keller, M., Bengio, S.: Theme topic mixture model: A graphical model for document representation. IDIAP Research Report, IDIAP-RR-04-05 (January 2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2003)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Madison (June 2003)
Monay, F., Gatica-Perez, D.: On image auto-annotation with latent space models. In: Proc. of ACM Int. Conf. on Multimedia, Berkeley (November 2003)
Monay, F., Gatica-Perez, D.: PLSA-based image auto-annotation: Constraining the latent space. In: Proc. ACM Int. Conf. on Multimedia, New York (October 2004)
Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Proc. of IEEE Europ. Conf. on Computer Vision, Prague (May 2004)
Quelhas, P., Monay, F., Odobez, J.-M., Gatica-Perez, D., Tuytelaars, T., Gool, L.V.: Modeling scenes with local descriptors and latent aspects. In: Proc. of IEEE Int. Conf. on Computer Vision, Beijing (October 2005)
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering object categories in image collections. Technical report, Dept. of Engineering Science, University of Oxford (2005)
Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proc. of IEEE Int. Conf. on Computer Vision, Nice (October 2003)
Tuytelaars, T., Van Gool, L.: Content-based image retrieval based on local affinely invariant regions. In: Proc. of Visual 1999, Amsterdam (June 1999)
Vailaya, A., Figueiredo, M., Jain, A., Zhang, H.J.: Image classification for content-based indexing. IEEE Trans. on Image Processing 10, 117–130 (2001)
Willamowski, J., Arregui, D., Csurka, G., Dance, C.R., Fan, L.: Categorizing nine visual classes using local appearance descriptors. In: Proc. of ICPR Workshop on Learning for Adaptable Visal Systems, Cambridge (August 2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Monay, F., Quelhas, P., Gatica-Perez, D., Odobez, JM. (2006). Constructing Visual Models with a Latent Space Approach. In: Saunders, C., Grobelnik, M., Gunn, S., Shawe-Taylor, J. (eds) Subspace, Latent Structure and Feature Selection. SLSFS 2005. Lecture Notes in Computer Science, vol 3940. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11752790_7
Download citation
DOI: https://doi.org/10.1007/11752790_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34137-6
Online ISBN: 978-3-540-34138-3
eBook Packages: Computer ScienceComputer Science (R0)