Sunday, June 13, 2010

Sven Dickinson at POCV 2010, ACVHL Tomorrow

This morning, Sven Dickinson gave a talk to start the POCV 2010 Workshop at CVPR2010.  For those of you who might not know, POCV stands for Perceptual Organization in Computer Vision.  While segmentation can be thought of as a perceptual grouping process, contiguous regions don't have to be the end product of a meaningful perceptual grouping process.  There are many popular and useful algorithms which group non-accidental contours yet come short of a full-blown image segmentation.

The title of Dickinson's talk was "The Role of Intermediate Shape Priors in Perceptual Grouping and Image Abstraction." In the beginning of his talk, Sven pointed out how perceptual organization was at its prime in the mid 90s and declined in the 2000s due to the popularity of machine learning and the "detection" task.  He believes that good perceptual grouping is what is going to make vision scale -- that is, without first squeezing out all that we can out of the bottom level we are doomed to fail.

Dickinsons showed some nice results from his most recent research efforts where objects are broken down into generic "parts" -- this reminded me of Biederman's geons, although Sven's fitting is done in the 2D image plane.  Sven emphasized that successful shape primitives must be category-independent if we are to have scalable recognition of thousands of visual concepts in images.  This is much different than the mainstream per-category object detection task which has been popularized by contests such as the PASCAL VOC.

While I personally believe that there is a good place for perceptual organization in vision, I wouldn't view it as the Holy Grail.  It is perhaps the Holy Bridge we must inevitably cross on the way to finding the Holy Grail.  I believe that for full-grown fully-functional members of society, our ability to effortlessly cope with the world is chiefly due to its simplicity and repeatability, and not due to some amazing internal perceptual organization algorithm.  Perhaps it is when we were children -- viewing the world through a psychedelic fog of innocence -- that perceptual grouping helped us cut up the world into meaningful entities.

A common theme in Sven's talk was the idea of Learning to Group in a category-independent way.  This means that all of the successes of Machine Learning aren't thrown out the door, and this appears to a quite different way of grouping than what has been done in the 1970s.

Tomorrow I will be at ACVHL Workshop "Advancing Computer Vision with Humans in the Loop".  I haven't personally "turked" yet, but I feel I will be jumping on the bandwagon soon.  Anyways, the keynote speakers should make for an awesome workshop.  They do not need introductions: David Forsyth, Aude Oliva, Fei-Fei Li, Antonio Torralba, and Serge Belongie -- all influential visionaries.