Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2012-02-28
Computer Science
Computer Vision and Pattern Recognition
Scientific paper
We describe a method for fast approximation of sparse coding. The input space is subdivided by a binary decision tree, and we simultaneously learn a dictionary and assignment of allowed dictionary elements for each leaf of the tree. We store a lookup table with the assignments and the pseudoinverses for each node, allowing for very fast inference. We give an algorithm for learning the tree, the dictionary and the dictionary element assignment, and In the process of describing this algorithm, we discuss the more general problem of learning the groups in group structured sparse modelling. We show that our method creates good sparse representations by using it in the object recognition framework of \cite{lazebnik06,yang-cvpr-09}. Implementing our own fast version of the SIFT descriptor the whole system runs at 20 frames per second on $321 \times 481$ sized images on a laptop with a quad-core cpu, while sacrificing very little accuracy on the Caltech 101 and 15 scenes benchmarks.
Gregor Karol
LeCun Yann
Szlam Arthur
No associations
LandOfFree
Fast approximations to structured sparse coding and applications to object classification 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 Fast approximations to structured sparse coding and applications to object classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast approximations to structured sparse coding and applications to object classification will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-522876