Event Location: NSH 1507
Bio: Tomasz Malisiewicz obtained his B.S. in Computer Science and Physics
from Rensselaer Polytechnic Institute (RPI) in 2005. He has been a PhD
student at Carnegie Mellon University’s Robotics Institute since 2005
and is advised by Alexei A. Efros. His research interests are in
computer vision and machine learning, focusing on multi-class object
recognition and segmentation. Since 2006 his research has been
supported by a National Science Foundation Graduate Research Fellowship.

Abstract: Many multi-class object recognition systems focus on categorization,
where the goal is to predict a novel object’s category given its feature
representation. In this talk, I pose the recognition problem as data
association. In this setting, a novel object is explained solely in
terms of a small set of exemplar objects to which it is visually
similar. Inspired by the work of Frome et al., we learn separate
distance functions for each exemplar; however, our distances are
interpretable on an absolute scale and can be thresholded to detect the
presence of an object. Our exemplars are represented as image regions
and the learned distances capture the relative importance of shape,
color, texture, and position features for that region. We use the
distance functions to detect and segment objects in novel images by
associating the bottom-up segments obtained from multiple image
segmentations with the exemplar regions. We evaluate the detection and
segmentation performance of our non-parametric exemplar-based system on
real-world outdoor scenes from the LabelMe dataset and also show some
promising qualitative image parsing results.