friday 24 april 2015
Since we had a few publications on the topic of distributed machine learning (in particular a Neurocomputing paper on distributed PCA: "Asynchronous Gossip Principal Components Analysis"), let's talk a bit more about it. My Ph.D. student Jérôme Fellus has rolled out the version first version of his libagml library. This is a distributed machine learning library in C++ that relies on Gossip protocols.
The main page is here: http://perso-etis.ensea.fr/~jerofell/software.html
The way it works is dead simple: you have a mother class that corresponds to a node, and all you have to do is derive it to make your specifi local computation and aggregation procedures. All the networking, instantiation, etc, is handle by the library. Nice, isn't it?
tuesday 03 march 2015
This post should explain why I did not set anything new here for long time. First, I've been very busy doing research the past year. In no particular order:
- My very first PhD student - Romain Negrel - has successfully defended in December 2014. He is now pursuing a postdoc at GREY, Caen, France.
- I've been invited for a month at the TU Darmstadt between August and September, working with Dr.-Ing. V. Willert and Thomas Guthier on learning local descriptors. While the work isn't finished yet (read not published), it is very interesting. All of this was funded by the DAAD, which I thank gratefully.
- I've been working a lot recently on computer vision and image processing for cultural heritage purposes. To that end, I've set up a benchmark using images from the BnF, based on a project we have funded by the Labex Patrima. A paper on that has been accepted in IEEE Signal Processing Magazine. With respect to the project, we are starting to work on interesting things involving deep learning with my new postdoc Yi Ren.
- More on cultural heritage and image processing, I'm organizing a special session at this year's edition of the GRETSI. The call for paper is here, you are of course all invited to submit as many paper as you can to share new work in this interesting area.
- I've been publishing many things in the past months (at my scale of course), all of which you can find in the publications page.
Now for the things scarcely related to research, I've been elected head of the computer science department at the ENSEA, which means that I now have a lot of administrative things to do. If you have any inquiries regarding CS at our graduate school, I guess I am now the guy to ask.
Also, I've been releasing an album with my oldest band, which you can download for free here.
monday 18 june 2012
We have a paper on image categorization accepted at ICPR next November. This is the other part of the Work Romain Negrel has been doing with VLAT. This time it's about efficiency in image classification. We tried to put every tricks of latest image categorization techniques (like dense sampling, spatial pyramid, and so on) into our VLAT while still retaining small size signatures.
All in all, we managed to achieve 61.5% mAP on VOC2007, which is not bad at all considering we used a single feature and a linear classifier (a stochastic gradient descent from Leon Bottou). Actually, if you put the throttle a bit further, you can expect better results, but then it becomes very heavy computationally speaking. As usual, some code is available here, although it's only for the Holydays dataset right now. At least you can produce the features and then use your own machine learning library (or mine, of course!).
monday 23 april 2012
We have a paper accepted at ICIP next september. This is the work Romain Negrel has beeing doing on trying to reduce the size of our VLAT features using some kernel based dimensionality reduction techniques. We focused on search by similarity, and it happened to give very comparable results for large scale benchmarks.
I hope to release some code on this very soon. At least you can check this page
I'll bee in Brugge next week for the ESANN conference.
monday 05 march 2012
On Friday morning, I received a nice email from Elsevier stating that, finally, one of my articles will be published. I don't really know what is the more irritating: The fact that it was accepted 2 years ago for publication, or the big spam at the end of the email promoting some totally stupid and useless stuff like certificates of publication.
Come on, Elsevier. I wrote this article back in 2009, and the peer review went fine so that it was accepted in early 2010. What is wrong with your publishing processes? Two years to get from the editor's desk to the printer is a bit long, isn't it? It is somehow disappointing to wait that much time.
Moreover, why would you think I would be interested in stupid gifts like a giant poster version of the first page, or a certificate of publication (at 35 euros each)? Sure I am proud of the work I did on this. But I am proud of the work in itself, not the way it is published. The fact that it took the shape of a journal article published by Elsevier rather than a technical report is just the same to me.
This job is sufficiently hard enough with all the bibliometric shit around, that I don't need some corporate consumerism on top of it. Now, please, just get off my lawn.