[Colloquium] [Talks at TTIC] REMINDER: 4/29 TTIC Colloquium: Bharath Hariharan, Cornell University

[Alicia McClarin]

*When:    *  Monday, April 29th at 11:00 am



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



*Who:        *Bharath Hariharan, Cornell University

*Title:         *Visual Learning with Fewer Labels

*Abstract:*  The performance of recognition systems has grown by leaps and
bounds these last 5 years. However, modern recognition systems still
require thousands of examples per class to train. Furthermore, expanding
the capabilities of the system by introducing new visual concepts again
requires collecting thousands of examples for the new concept. In contrast,
humans are known to quickly learn new visual concepts from as few as 1
example, and indeed require very little labeled data to build their
powerful visual systems from scratch. The requirement for large training
sets also makes it infeasible to use current machine vision systems for
rare or hard-to-annotate visual concepts or new imaging modalities.

I will talk about some of our work on reducing this need for large labeled
training sets. This will include three broad directions: new ways of
learning feature representations, new learnt data augmentation strategies,
and new possibilities for re-thinking the problem setup, all with the aim
of reducing the annotation cost for building new recognition systems. I
will also discuss how this question of supervision plays out for other
“richer” computer vision tasks beyond image classification, and how
thinking carefully about how we teach machines to do tasks can lead to rich
dividends.

*Host: *Greg Shakhnarovich <greg at ttic.edu>

-- 
*Alicia McClarin*
*Toyota Technological Institute at Chicago*
*6045 S. Kenwood Ave., **Office 510*
*Chicago, IL 60637*
*773-702-5370*
*www.ttic.edu* <http://www.ttic.edu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20190426/0f900b48/attachment.html>