Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2011-09-29
Computer Science
Computer Vision and Pattern Recognition
9 pages, 8 figures
Scientific paper
Sparse coding is a proven principle for learning compact representations of images. However, sparse coding by itself often leads to very redundant dictionaries. With images, this often takes the form of similar edge detectors which are replicated many times at various positions, scales and orientations. An immediate consequence of this observation is that the estimation of the dictionary components is not statistically efficient. We propose a factored model in which factors of variation (e.g. position, scale and orientation) are untangled from the underlying Gabor-like filters. There is so much redundancy in sparse codes for natural images that our model requires only a single dictionary element (a Gabor-like edge detector) to outperform standard sparse coding. Our model scales naturally to arbitrary-sized images while achieving much greater statistical efficiency during learning. We validate this claim with a number of experiments showing, in part, superior compression of out-of-sample data using a sparse coding dictionary learned with only a single image.
Bengio Yoshua
Bergstra James
Courville Aaron
No associations
LandOfFree
The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All) does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All), we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All) will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-152832