We provide some Matlab package corresponding to our CVPR‘2010 paper on compact image representations. It describe a large scale image indexing system with a very compact image representation (an image is typically represented by 16 to 40 bytes).
The package is available here.
The Yael library provides efficient implementations of computationally demanding functions, such as kmeans and exact k-nearest neighbors search (used, e.g., to assign descriptor to visual words based on a k-means codebook). It offers a C, python and Matlab (Mex) interface.
See the overview paper.
A Matlab/Mex implementation of the ASMK* variant (good compromise accuracy/speed/memory) is available here. The method is described in this paper.
GIST is a global descriptor originally designed by Antonio Torralba and Aude Oliva. These authors provide a matlab implementation of this descriptor.
Download our own C implementation of GIST (by Matthijs Douze and Christophe Smekens) that we developped for our CIVR‘2009 paper: “Evaluation of GIST descriptors for web-scale image search”.
Anti-sparse coding is a technique that is opposite in spirit to sparse coding: Instead of trying to concentrate the signal on a few components, the objective of these so-called “spread representations” is to use almost all the components so that all have a comparable contribution to the final reconstruction.
This link provides the Matlab package that reproduces some results of our paper Anti-sparse coding for approximate nearest neighbor search. It includes the L-infinity solver used to produce the spread representations.
