# HG changeset patch # User rlm # Date 1365626332 14400 # Node ID f1b8727360fbd0e59994379f8c8027874c264167 # Parent 8e62bf52be59763998a2d10eb63ca39f70f6adbe add images. diff -r 8e62bf52be59 -r f1b8727360fb images/viola-parzen-1.png Binary file images/viola-parzen-1.png has changed diff -r 8e62bf52be59 -r f1b8727360fb images/viola-parzen-2.png Binary file images/viola-parzen-2.png has changed diff -r 8e62bf52be59 -r f1b8727360fb org/ullman.org --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/org/ullman.org Wed Apr 10 16:38:52 2013 -0400 @@ -0,0 +1,145 @@ +#+title: Ullman Literature Review +#+author: Robert McIntyre +#+email: rlm@mit.edu +#+description: Review of some of the AI works of Professor Shimon Ullman. +#+keywords: Shimon, Ullman, computer vision, artificial intelligence, literature review +#+SETUPFILE: ../../aurellem/org/setup.org +#+INCLUDE: ../../aurellem/org/level-0.org +#+babel: :mkdirp yes :noweb yes :exports both + + +* Ullman + +Actual code reuse! + +precision = fraction of retrieved instances that are relevant + (true-postives/(true-positives+false-positives)) + +recall = fraction of relevant instances that are retrieved + (true-positives/total-in-class) + +cross-validation = train the model on two different sets to prevent +overfitting. + +nifty, relevant, realistic ideas +He doesn't confine himself to unplasaubile assumptions + +** Our Reading + +*** 2002 Visual features of intermediate complexity and their use in classification + + + + +** Getting around the dumb "fixed training set" methods + +*** 2006 Learning to classify by ongoing feature selection + + Brings in the most informative features of a class, based on + mutual information between that feature and all the examples + encountered so far. To bound the running time, he uses only a + fixed number of the most recent examples. He uses a replacement + strategy to tell whether a new feature is better than one of the + corrent features. + +*** 2009 Learning model complexity in an online environment + + Sort of like the heirichal baysean models of Tennanbaum, this + system makes the model more and more complicated as it gets more + and more training data. It does this by using two systems in + parallell and then whenever the more complex one seems to be + needed by the data, the less complex one is thrown out, and an + even more complex model is initialized in its place. + + He uses a SVM with polynominal kernels of varying complexity. He + gets good perfoemance on a handwriting classfication using a large + range of training samples, since his model changes complexity + depending on the number of training samples. The simpler models do + better with few training points, and the more complex ones do + better with many training points. + + The final model had intermediate complexity between published + extremes. + + The more complex models must be able to be initialized efficiently + from the less complex models which they replace! + + +** Non Parametric Models + +[[../images/viola-parzen-1.png]] +[[../images/viola-parzen-2.png]] + +*** 2010 The chains model for detecting parts by their context + + Like the constelation method for rigid objects, but extended to + non-rigid objects as well. + + Allows you to build a hand detector from a face detector. This is + usefull because hands might be only a few pixels, and very + ambiguous in an image, but if you are expecting them at the end of + an arm, then they become easier to find. + + They make chains by using spatial proximity of features. That way, + a hand can be idntified by chaining back from the head. If there + is a good chain to the head, then it is more likely that there is + a hand than if there isn't. Since there is some give in the + proximity detection, the system can accomodate new poses that it + has never seen before. + + Does not use any motion information. + +*** 2005 A Hierarchical Non-Parametric Method for Capturing Non-Rigid Deformations + + (relative dynamic programming [RDP]) + + Goal is to match images, as in SIFT, but this time the images can + be subject to non rigid transformations. They do this by finding + small patches that look the same, then building up bigger + patches. They get a tree of patches that describes each image, and + find the edit distance between each tree. Editing operations + involve a coherent shift of features, so they can accomodate local + shifts of patches in any direction. They get some cool results + over just straight correlation. Basically, they made an image + comparor that is resistant to multiple independent deformations. + + !important small regions are treated the same as nonimportant + small regions + + !no conception of shape + + quote: + The dynamic programming procedure looks for an optimal + transformation that aligns the patches of both images. This + transformation is not a global transformation, but a composition + of many local transformations of sub-patches at various sizes, + performed one on top of the other. + +*** 2006 Satellite Features for the Classification of Visually Similar Classes + + Finds features that can distinguish subclasses of a class, by + first finding a rigid set of anghor features that are common to + both subclasses, then finding distinguishing features relative to + those subfeatures. They keep things rigid because the satellite + features don't have much information in and of themselves, and are + only informative relative to other features. + +*** 2005 Learning a novel class from a single example by cross-generalization. + + Let's you use a vast visual experience to generate a classifier + for a novel class by generating synthetic examples by replaceing + features from the single example with features from similiar + classes. + + quote: feature F is likely to be useful for class C if a similar + feature F proved effective for a similar class C in the past. + + Allows you to trasfer the "gestalt" of a similiar class to a new + class, by adapting all the features of the learned class that have + correspondance to the new class. + +*** 2007 Semantic Hierarchies for Recognizing Objects and Parts + + Better learning of complex objects like faces by learning each + piece (like nose, mouth, eye, etc) separately, then making sure + that the features are in plausable positions.