A UdeM-McGill-mPrime machine learning seminar will be held tomorrow,
Thursday, June 7th. The talk given by Karim Ali, will take place from
15h00-16h00. The talk will be held at the Université de Montréal, room
AA3195. Hope to see you there !
Title: Learning to detect objects with minimal supervision
Abstract
Many classes of objects can now be successfully detected with
statistical machine learning techniques. Faces, cars and pedestrians,
have all been detected with low error rates by learning their
appearance in a highly generic manner from extensive training sets.
These recent advances have enabled the use of reliable object
detection components in real systems, such as automatic face focusing
functions on digital cameras. One key drawback of these methods, and
the issue addressed here, is the prohibitive requirement that training
sets contain thousands of manually annotated examples. We present two
methods which make headway toward reducing labeling requirements and
in turn, toward a tractable solution to the general detection problem.
First, we propose a new learning strategy for object detection. The
proposed scheme forgoes the need to train a collection of detectors
dedicated to homogeneous families of poses, and instead learns a
single classifier that has the inherent ability to deform based on the
signal of interest. We train a detector with a standard AdaBoost
procedure by using combinations of pose-indexed features and pose
estimators. This allows the learning process to select and combine
various estimates of the pose with features able to compensate for
variations in pose without the need to label data for training or
explore the pose space in testing.
Second, we propose a new learning method which exploits temporal
consistency to successfully learn a complex appearance model from a
sparsely labeled training video. Our approach consists in iteratively
improving an appearance-based model built with a Boosting procedure,
and the reconstruction of trajectories corresponding to the motion of
multiple targets. We demonstrate the efficiency of our procedure by
learning a pedestrian detector from videos and a cell detector from
microscopy image sequences.
