Peekaboo

The ICML2012 accepted papers are officially online . On twitter , Andrej Kaparthy complained that the list is a bit hard to browse through. I agree and even though this is probably not the nice visualization he had in mind, I felt like having topical reading lists would somehow mitigate this problem. Here is my reading list on deep learning and unsupervised feature extraction: A Generative Process for Contractive Auto-Encoders Salah Rifai, Yann Dauphin, Pascal Vincent, Yoshua Bengio – Accepted Abstract: The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of the Jacobian of the transformation from input to representation. The corresponding singular values specify how much local variation is plausible in directions associated with the corresponding singular vectors, whi...

ICCV! In Barcelona! Regrettably, I had to stay home in cold Bonn. Today, I went through the accepted papers, and one of the many I found interesting was "Ask the locals: multi-way local pooling for image recognition" by  Y-Lan Boureau, Nicolas Le Roux, Francis Bach, Jean Ponce and Yann LeCun. Many big names on this one :) In this work the authors highlight a feature of many recent coding algorithms for visual descriptors: locality in the feature space. They formulate the encoding as a maximum pooling operation that is local in an image as well as in features space, by using a coarse k-means clustering on features (that are histograms of sparse codes if I understood correctly). The paper reports very good results on Caltech 101 and 256, and the scenes dataset. In particular, good results are achieved with quite small dictionaries, i.e. of size 256. My colleague Hannes pointed out that the features space binning is basically a layer of an RBF network. Which is not menti...

Today I stumbled upon mahotas , a python image processing library while researching local binary patterns on wikipedia. I haven't found many of those yet and this one seems to be very active at the moment and quite mature. The library includes I/O and has many low-level vision features, like thresholding, watershed, labeling, distance transform, convex hulls, etc. I was missing something like this, so I quite like it. Descriptors such as SURF and obviously LBP are also included - which is very nice since I am often having a hard time finding nice Python bindings for image features! I hope work on this library continues and maybe it'll include more features and more segmentation methods in the future :)