NIPS 2010 - More Highlights

This post is about all the other papers on NIPS that I found particularly interesting but don't have the time to write a lot about.
There is a similar post at Yaroslav Bulato's blog.
  • Multiple Kernel Learning and the SMO Algorithm by Vishwanathan, Sun, Ampornput and Varma (pdf) . Code here.
    Efficient training of p-norm MKL using Sequential Minimal Optimization.
  • Kernel Descriptors for Visual Recognition by
    Liefeng Bo, Xiaofeng Ren, Dieter Fox (pdf)
    A general setting to design image patch descriptors using kernels. The proposed kernel is demonstrated to outperform SIFT.
  • A Theory of Multiclass Boosting  by Indraneel Mukherjee, Robert Schapire (pdf)
    Title says it all.
  • Deep Coding Network  by Yuanqing Lin, Zhang Tong, Shenghuo Zhu, Kai Yu (pdf)
    This is a continuation of the work on Linear Coordinate Coding (pdf) which won the image net callenge.
  • Tree-Structured Stick Breaking for Hierarchical Data  by Ryan Adams, Zoubin Ghahramani, Michael Jordan (pdf)
    This is work on hierarchical topic models using trees. I must confess I have not ultimately understood this work but I find it highly interesting. In contrast to nested Chinese Restaurant Processes(pdf ), samples from the distribution can also be inner nodes.
  • Segmentation as Maximum-Weight Independent Set  by William Brendel, Sinisa Todorovic (pdf)
    This work on image segmentation formulates consistent segmentations using graphs and introduces a new optimization algorithm to approximately find independent sets.
    This work is quite similar to a tech report from Adrian Ion (pdf) but focuses more on optimization than on the potentials for the graph.
  • Simultaneous Object Detection and Ranking with Weak Supervision  by Matthew Blaschko, Andrea Vedaldi, Andrew Zisserman (pdf)
    A multiple instance approach to finding objects in weakly labeled images using something like a "latent SVR".
  • Convex Multiple-Instance Learning by Estimating Likelihood Ratio  by Fuxin Li, Cristian Sminchisescu (pdf)
    Multiple instance learning using a novel convex formulation. This is a promising direction and hopefully will be applied soon to object segmentation using "Object Recognition as Ranking Holistic Figure-Ground Hypotheses" (pdf) by the same group.

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