nips nips2004 nips2004-99 nips2004-99-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Andras D. Ferencz, Erik G. Learned-miller, Jitendra Malik
Abstract: We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular instance (as we may be provided with only one “training” example of it), we can use information extracted from observing other members of the class. We pose this task as a learning problem, in which the learner is given image pairs, labeled as matching or not, and must discover which image features are most consistent for matching instances and discriminative for mismatches. We explore a patch based representation, where we model the distributions of similarity measurements defined on the patches. Finally, we describe an algorithm that selects the most salient patches based on a mutual information criterion. This algorithm performs identification well for our challenging dataset of car images, after matching only a few, well chosen patches. 1
[1] Y. Amit and D. Geman. A computational model for visual selection. Neural Computation, 11(7), 1999.
[2] D. Beymer, P. McLauchlan, B. Coifman, and J. Malik. A real-time computer vision system for measuring traffic parameters. CVPR, 1997.
[3] B. Efron, T. Hastie, I. Johnstone, and R. Tibshirani. Least angle regression. Annals of Statistics, 32(2):407–499, 2004.
[4] T. Kadir and M. Brady. Scale, saliency and image description. International Journal of Computer Vision, 45(2):83–105, 2001.
[5] F. Li, R. Fergus, and P. Perona. A Bayesian approach to unsupervised one-shot learning of object categories. In ICCV, 2003.
[6] D. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110, 2004.
[7] P. McCullagh and J. A. Nelder. Generalized Linear Models. Chapman and Hall, 1989.
[8] E. Miller, N. Matsakis, and P. Viola. Learning from one example through shared densities on transforms. In CVPR, 2000.
[9] H. Pasula, S. Russell, M. Ostland, and Y. Ritov. Tracking many objects with many sensors. IJCAI, 1999.
[10] H. Schneiderman and T. Kanade. A statistical approach to 3d object detection applied to faces and cars. CVPR, 2000.
[11] M. Tarr and I. Gauthier. FFA: A flexible fusiform area for subordinate-level visual processing automatized by expertise. Nature Neuroscience, 3(8):764–769, 2000.
[12] M. Vidal-Naquet and S. Ullman. Object recognition with informative features and linear classification. In International Conference on Computer Vision, 2003.
[13] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In CVPR, 2001.
[14] M. Weber, M. Welling, and P. Perona. Unsupervised learning of models for recognition. ECCV, 2000. 7 Answer to Figure 1: top left matches bottom center; bottom left matches bottom right. For our algorithm, matching these images was not a challenge.