Orateur : Donald Geman, CMLA / Johns Hopkins University
Titre : Stationary Features and Cat Detection
Résumé :
Most discriminative techniques for detecting and describing instances
from object categories in still images consist of looping over a
partition of a pose space with dedicated binary classifiers. This
strategy is inefficient for a complex pose: fragmenting the training
data severely reduces accuracy, and the computational cost is
prohibitive due to visiting a massive pose partition. To overcome
data-fragmentation I will discuss a novel framework centered on
pose-indexed features, which allows for efficient, one-shot learning
of pose-specific classifiers. Such features assign a response to a
pair consisting of an image and a pose, and are designed so that the
probability distribution of the response is invariant if an object is
actually present. To avoid expensive scene processing, the classifiers
are arranged in a hierarchy based on nested partitions of the pose,
which allows for efficient search. The hierarchy is then "folded" for
training: all the classifiers at each level are derived from one base
predictor learned from all the data. The hierarchy is "unfolded" for
testing: parsing a scene amounts to examining increasingly finer
object descriptions only when there is sufficient evidence for coarser
ones. I will illustrate these ideas by detecting and localizing cats
in highly cluttered greyscale scenes. This is joint work with
Francois Fleuret.
 |
CMLA UMR 8536 |
 |