CVML 2011 Posters

There were many posters on the CVML summer school and I won't talk about all of them.
Actually 8 of them got prizes (in form of hand-signed CV and ML books).
I knew some of the work form NIPS2010 but there were some things that were new to me:

Alexander Vezhnevets presented work on Multi Image Model for Semantic Segmentation with Different Levels of Supervision.
I don't know how I could miss that before. This is amazing work on weakly supervised semantic scene segmentation on MSRC. It makes use of CRFs, boosted texton forests and superpixels. The CRF does not only connect neighbouring superpixels but also superpixels in different images that look similar. Super pixel labels are treated as latent variables and only a very simple contraint between image label and superpixel label is enforced.

Since I am looking at a very similar task at the moment, even though the other posters were very good, this one was definitely the best for me.


Yang Hua presented work on Contextualizing Object Detection and Classification. This work was very successful in last years PASCAL challenge and was presented in (this years?) CVPR.
The basic idea is quite simple (but of course there is loads of features and tuning involved to make it win). Classifiers are trained per class and applied to images using sliding windows.
Then for each class, the confidences of the two best bounding boxes are used as an additional feature, giving 2x20 real numbers. On these, an additional classifier is trained and combined with the "direct" per class classifier.

Another idea that was included in this work was exclusiveness of labels. In the Pascal dataset, the classes have strong correlations. The authors argue that it is rather hard to use this correlations directly but instead construct exclusive label sets, which are sets of labels that never cooccur (like airplane and potted plant). This exclusiveness is then enforced in the predictions (though I am a little unsure about the details at the moment).

Comments

Post a Comment

Popular posts from this blog

Machine Learning Cheat Sheet (for scikit-learn)

Image
As you hopefully have heard, we at scikit-learn are doing a user survey (which is still open by the way). One of the requests there was to provide some sort of flow chart on how to do machine learning. As this is clearly impossible, I went to work straight away. This is the result: [edit2] clarification: With ensemble classifiers and ensemble regressors I mean random forests , extremely randomized trees, gradient boosted trees , and the soon-to-be-come weight boosted trees (adaboost). [/edit2] Needless to say, this sheet is completely authoritative.
Read more

A Wordcloud in Python

Image
Last week I was at Pycon DE , the German Python conference. After hacking on scikit-learn a lot last week, I decided to to something different on my way back, that I had planned for quite a while: doing a wordl -like word cloud . I know, word clouds are a bit out of style but I kind of like them any way. My motivation to think about word clouds was that I thought these could be combined with topic-models to give somewhat more interesting visualizations. So I looked around to find a nice open-source implementation of word-clouds ... only to find none. (This has been a while, maybe it has changed since). While I was bored in the train last week, I came up with this code . A little today-themed taste:
Read more

MNIST for ever....

Image
[update] This post is a bit old, but many people still seem interested. So just a short update: Nowadays I would use Python and scikit-learn to do this. Here is an example of how to do cross-validation for SVMs in scikit-learn. Scikit-learn even downloads MNIST for you. [/update] MNIST is, for better or worse, one of the standard benchmarks for machine learning and is also widely used in then neural networks community as a toy vision problem. Just for the unlikely case that anyone is not familiar with it: It is a dataset of handwritten digits, 0-9, in black on white background. It looks something like this: There are 60000 training and 10000 test images, each 28x28 gray scale. There are roughly the same number of examples of each category in the test and training datasets. I used it in some papers myself even though there are some reasons why it is a little weird. Some not-so-obvious (or maybe they are) facts are: - The images actually contain a 20x20 patch of digi...
Read more

Python things you never need: Empty lambda functions

Ever wanted to create an empty Python function in-line? No? Me neither. But my coworker does... We found the answer: <pre> x = lambda : None </pre> If you ever needed this, please tell me ;) [Edit] Apparently some people do need it :) Btw, most people seem to try Most people try lambda: pass first. But you have to remember, the thing at the right side of the colon is the return value of the function, not the body! So an expression is needed, not a statement. [\Edit]
Read more