Alan Yuille
Unsupervised Structure Learning: Hierarchical Recursive Composition,
Suspicious Coincidence and Competitive Exclusion.
We describe a new method for unsupervised structure learning of a
hierarchical compositional model (HCM) for deformable objects. The learning
is unsupervised in the sense that we are given a training dataset of images
containing the object in cluttered backgrounds but we do not know the
position or boundary of the object. The structure learning is performed by a
bottom-up and top-down process. The bottom-up process is a novel form of
hierarchical clustering which recursively composes proposals for simple
structures to generate proposals for more complex structures. We combine
standard clustering with the suspicious coincidence principle and the
competitive exclusion principle to prune the number of proposals to a
practical number and avoid an
exponential explosion of possible structures. The hierarchical clustering
stops automatically, when it fails to generate new proposals, and outputs a
proposal for the object model. The top-down process validates the proposals
and fills in missing elements. We tested our approach by
using it to learn a hierarchical compositional model for parsing and
segmenting horses on Weizmann dataset. We show that the resulting model is
comparable with (or better than) alternative methods. The versatility of our
approach is demonstrated by learning models for other objects (e.g., faces,
pianos, butterflies, monitors, etc.). It is worth noting that
the low-levels of the object hierarchies automatically learn generic image
features while the higher levels learn object specific features. We then
describe more recent work which uses similar principles to learn hierarchies
for many objects simultaneously.
This talk is based on two research projects. The full authors for these projects are:
- Project 1 (ECCV 2008) L. Zhu (UCLA), C. Lin (Microsoft Beijing), H.
Huang (Microsoft Beijing), Y.Chen (USTC), and A.L. Yuille (UCLA),
- Project 2. L. Zhu (MIT), Y. Chen (USTC), W. Freeman (MIT), A. Torrabla (MIT), and A.L. Yuille (UCLA).
Brief Bio.
Alan Yuille did his BA in Mathematics and his PhD in Theoretical Physics (Quantum Gravity) at Cambridge University. He was a NATO postdoc in Theoretical Physics at UT Austin and UC Santa Barbara. Then he moved to the MIT AI Lab as a research scientist and started working on computational models of vision. He then spent ten years in the Harvard Robotics Lab in the Division of Applied Sciences rising to the level of Associate Professor. After six years as senior research scientist at the Smith-Kettlewell Eye Research Institute he moved to the University of California at Los Angeles. He currently holds joint appointments in the Departments of Statistics, Computer Science, and Psychology and is a Fellow of IEEE.