Discriminative Decorrelation for Clustering and Classification
- Cite this paper as:
- Hariharan B., Malik J., Ramanan D. (2012) Discriminative Decorrelation for Clustering and Classification. In: Fitzgibbon A., Lazebnik S., Perona P., Sato Y., Schmid C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7575. Springer, Berlin, Heidelberg
Object detection has over the past few years converged on using linear SVMs over HOG features. Training linear SVMs however is quite expensive, and can become intractable as the number of categories increase. In this work we revisit a much older technique, viz. Linear Discriminant Analysis, and show that LDA models can be trained almost trivially, and with little or no loss in performance. The covariance matrices we estimate capture properties of natural images. Whitening HOG features with these covariances thus removes naturally occuring correlations between the HOG features. We show that these whitened features (which we call WHO) are considerably better than the original HOG features for computing similarities, and prove their usefulness in clustering. Finally, we use our findings to produce an object detection system that is competitive on PASCAL VOC 2007 while being considerably easier to train and test.
Unable to display preview. Download preview PDF.