[Colloquium] Re: REMINDER: 8/31 TTIC Colloquium: Kate Saenko, Boston University

[Mary Marre via Colloquium]

*PLEASE NOTE: SPECIAL DAY*

When:    * Thursday**,*  August 31st at 11:00 a.m.

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

Who:       Kate Saenko, Boston University


Title:      Distribution Alignment for Visual Domain Adaptation


Abstract:
Traditional supervised learning suffers from poor generalization when the
test data distribution differs from the training one. For example, if an
autonomous driving model is trained on a dataset collected in specific
weather conditions and/or geographical locations, its performance is likely
to drop significantly in novel test conditions and locations. Domain
adaptation solves this problem by transferring knowledge between domains. In
this talk, I will discuss recent work focusing on domain adaptation in
unsupervised scenarios, where the target domain is assumed to have no
annotated labels. Specifically, I will describe a generalized framework
based on end-to-end unsupervised domain alignment using domain-adaptive
losses, such as the adversarial, maximum mean discrepancy, and correlation
alignment losses.

Bio:
Prof. Kate Saenko is an Assistant Professor at the Computer Science
Department at Boston University, the director of the Computer Vision and
Learning Group and a member of the Image and Video Computing group. Her
past positions include Assistant Professor at the UMass Lowell CS
department, Postdoctoral Researcher at the International Computer Science
Institute, a Visiting Scholar at UC Berkeley EECS and a Visiting
Postdoctoral Fellow in the School of Engineering and Applied Science at
Harvard University. Her research interests are in developing machine
learning for image and language understanding, multimodal perception for
autonomous systems, and adaptive machine learning.


Host: Karen Livescu <klivescu at ttic.edu>

For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Wed, Aug 30, 2017 at 1:16 PM, Mary Marre <mmarre at ttic.edu> wrote:

> *PLEASE NOTE: SPECIAL DAY*
>
> When:    * Thursday**,*  August 31st at 11:00 a.m.
>
> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
> Who:       Kate Saenko, Boston University
>
>
> Title:      Distribution Alignment for Visual Domain Adaptation
>
>
> Abstract:
> Traditional supervised learning suffers from poor generalization when the
> test data distribution differs from the training one. For example, if an
> autonomous driving model is trained on a dataset collected in specific
> weather conditions and/or geographical locations, its performance is likely
> to drop significantly in novel test conditions and locations. Domain
> adaptation solves this problem by transferring knowledge between domains. In
> this talk, I will discuss recent work focusing on domain adaptation in
> unsupervised scenarios, where the target domain is assumed to have no
> annotated labels. Specifically, I will describe a generalized framework
> based on end-to-end unsupervised domain alignment using domain-adaptive
> losses, such as the adversarial, maximum mean discrepancy, and correlation
> alignment losses.
>
> Bio:
> Prof. Kate Saenko is an Assistant Professor at the Computer Science
> Department at Boston University, the director of the Computer Vision and
> Learning Group and a member of the Image and Video Computing group. Her
> past positions include Assistant Professor at the UMass Lowell CS
> department, Postdoctoral Researcher at the International Computer Science
> Institute, a Visiting Scholar at UC Berkeley EECS and a Visiting
> Postdoctoral Fellow in the School of Engineering and Applied Science at
> Harvard University. Her research interests are in developing machine
> learning for image and language understanding, multimodal perception for
> autonomous systems, and adaptive machine learning.
>
>
> Host: Karen Livescu <klivescu at ttic.edu>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757 <(773)%20834-1757>*
> *f: (773) 357-6970 <(773)%20357-6970>*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
> On Fri, Aug 25, 2017 at 10:31 AM, Mary Marre <mmarre at ttic.edu> wrote:
>
>> *PLEASE NOTE: SPECIAL DAY*
>>
>> When:    * Thursday**,*  August 31st at 11:00 a.m.
>>
>> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:       Kate Saenko, Boston University
>>
>>
>> Title:      Distribution Alignment for Visual Domain Adaptation
>>
>>
>> Abstract:
>> Traditional supervised learning suffers from poor generalization when the
>> test data distribution differs from the training one. For example, if an
>> autonomous driving model is trained on a dataset collected in specific
>> weather conditions and/or geographical locations, its performance is likely
>> to drop significantly in novel test conditions and locations. Domain
>> adaptation solves this problem by transferring knowledge between domains. In
>> this talk, I will discuss recent work focusing on domain adaptation in
>> unsupervised scenarios, where the target domain is assumed to have no
>> annotated labels. Specifically, I will describe a generalized framework
>> based on end-to-end unsupervised domain alignment using domain-adaptive
>> losses, such as the adversarial, maximum mean discrepancy, and correlation
>> alignment losses.
>>
>> Bio:
>> Prof. Kate Saenko is an Assistant Professor at the Computer Science
>> Department at Boston University, the director of the Computer Vision and
>> Learning Group and a member of the Image and Video Computing group. Her
>> past positions include Assistant Professor at the UMass Lowell CS
>> department, Postdoctoral Researcher at the International Computer Science
>> Institute, a Visiting Scholar at UC Berkeley EECS and a Visiting
>> Postdoctoral Fellow in the School of Engineering and Applied Science at
>> Harvard University. Her research interests are in developing machine
>> learning for image and language understanding, multimodal perception for
>> autonomous systems, and adaptive machine learning.
>>
>>
>> Host: Karen Livescu <klivescu at ttic.edu>
>>
>> For more information on the colloquium series or to subscribe to the
>> mailing list, please see http://www.ttic.edu/colloquium.php
>>
>>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 504*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757 <(773)%20834-1757>*
>> *f: (773) 357-6970 <(773)%20357-6970>*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170831/9105c195/attachment-0001.html>