[Colloquium] REMINDER: Research at TTIC: Michael Maire, TTIC

[Dawn Ellis]

When:     Friday, October 17, 2014 at noon

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:       Michael Maire, TTIC

Title:        Reconstructive Sparse Code Transfer for Contour Detection and
               Semantic Labeling

Abstract:

I will describe recent work on framing the task of predicting a semantic
labeling as a sparse reconstruction procedure.  This procedure applies a
target-specific learned transfer function to a generic deep sparse code
representation of an image.  This strategy partitions training into two
distinct stages.  First, in an unsupervised manner, we learn a set of
dictionaries optimized for sparse coding of image patches.  These
generic dictionaries minimize error with respect to representing image
appearance and are independent of any particular target task.  We train
a multilayer representation via recursive sparse dictionary learning on
pooled codes output by earlier layers.  Second, we encode all training
images with the generic dictionaries and learn a transfer function that
optimizes reconstruction of patches extracted from annotated
ground-truth given the sparse codes of their corresponding image
patches.  At test time, we encode a novel image using the generic
dictionaries and then reconstruct using the transfer function.  The
output reconstruction is a semantic labeling of the test image.

Applying this strategy to the task of contour detection, we demonstrate
performance competitive with state-of-the-art systems.  Unlike almost
all prior work, our approach obviates the need for any form of
hand-designed features or filters.  Our model is entirely learned from
image and ground-truth patches, with only patch sizes, dictionary sizes
and sparsity levels, and depth of the network as chosen parameters.  To
illustrate the general applicability of our approach, we also show
initial results on the task of semantic part labeling of human faces.

The effectiveness of our data-driven approach opens new avenues for
research on deep sparse representations.  Our classifiers utilize this
representation in a novel manner.  Rather than acting on nodes in the
deepest layer, they attach to nodes along a slice through multiple
layers of the network in order to make predictions about local patches.
Our flexible combination of a generatively learned sparse representation
with discriminatively trained transfer classifiers extends the notion of
sparse reconstruction to encompass arbitrary semantic labeling tasks.

Joint work with Stella Yu and Pietro Perona.  Paper to appear in ACCV
2014.
Abstract:


***************************************
Research at TTIC Seminar Series

TTIC is hosting a weekly seminar series presenting the research currently
underway at the Institute. Every week a different TTIC faculty member will
present their research.  The lectures are intended both for students
seeking research topics and adviser, and for the general TTIC and
University of Chicago communities interested in hearing what their
colleagues are up to.

To receive announcements about the seminar series, please subscribe to the
mailing list: https://groups.google.com/a/ttic.edu/group/talks/subscribe

Speaker details can be found at: http://www.ttic.edu/tticseminar.php.

For additional questions, please contact David McAllester at
mcallester at ttic.edu


-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20141016/484bb335/attachment.htm