Object localization by subspace clustering of local descriptors

Authors:
C. Bouveyron;J. Kannala;C. Schmid;S. Girard
Affiliations:
INRIA Rhône-Alpes, Saint-Ismier, France;Machine Vision Group, dept. of Electrical and Information Engineering, University of Oulu, Finland;INRIA Rhône-Alpes, Saint-Ismier, France;INRIA Rhône-Alpes, Saint-Ismier, France
Venue:
ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
Year:
2006

Citing 10
Cited 1

Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
Mixtures of probabilistic principal component analyzers

Neural Computation
Principal Manifolds and Probabilistic Subspaces for Visual Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning a Sparse Representation for Object Detection

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
An introduction to variable and feature selection

The Journal of Machine Learning Research
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Subspace clustering for high dimensional data: a review

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
Discovering Objects and their Localization in Images

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
The 2005 PASCAL visual object classes challenge

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment

Robust supervised classification with mixture models: Learning from data with uncertain labels

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a probabilistic approach for object localization which combines subspace clustering with the selection of discriminative clusters. Clustering is often a key step in object recognition and is penalized by the high dimensionality of the descriptors. Indeed, local descriptors, such as SIFT, which have shown excellent results in recognition, are high-dimensional and live in different low-dimensional subspaces. We therefore use a subspace clustering method called High-Dimensional Data Clustering (HDDC) which overcomes the curse of dimensionality. Furthermore, in many cases only a few of the clusters are useful to discriminate the object. We, thus, evaluate the discriminative capacity of clusters and use it to compute the probability that a local descriptor belongs to the object. Experimental results demonstrate the effectiveness of our probabilistic approach for object localization and show that subspace clustering gives better results compared to standard clustering methods. Furthermore, our approach outperforms existing results for the Pascal 2005 dataset.