[Colloquium] [Talks at TTIC] 5/13 Young Researcher Seminar Series: Richard Zhang, Adobe Research

[Alicia McClarin]

When:     *Monday, May 13th at 11:00 am *Please note special day* *

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

*Who:*       Richard Zhang, Adobe Research


*Title: *Image Synthesis for Self-Supervised Representation Learning


*Abstract: *In recent years, deep convolutional networks have proven to be
extremely adept at *discriminative* labeling tasks. Not only do networks
solve the direct task, they also learn an effective,
general representation of the visual world. We explore the use of deep
networks for image *generation*, or synthesis. Generation is challenging,
as it is difficult to characterize the perceptual quality of an image, and
often times there is more than one “correct” answer. However, we show that
networks can indeed perform the graphics task of image generation, and in
doing so, learn a representation of the visual world, even without the need
for hand-curated labels.



We propose BicycleGAN, a general system for image-to-image translation
problems, with the specific aim of capturing the multimodal nature of the
output space. We further study image colorization and develop automatic and
user-guided approaches. Moreover, colorization, as well as general
cross-channel prediction, is a simple but powerful pretext task
for self-supervised representation learning. We demonstrate strong transfer
to high-level semantic tasks, such as image classification, and to
low-level human perceptual similarity judgments. For the latter, we collect
a large-scale dataset of human judgments and find that our method
outperforms traditional metrics such as PSNR and SSIM. We also discover
that many unsupervised and self-supervised representations transfer
strongly, even comparable to fully-supervised methods. Despite their strong
transfer performance, deep convolutional representations surprisingly lack
a basic low-level property -- shift-invariance. We propose to incorporate a
classic but overlooked signal processing technique, low-pass filtering,
into modern deep network architectures.



*Bio:*       Richard Zhang is a research scientist at Adobe Research, San
Francisco. He recently obtained his PhD in EECS at UC Berkeley, advised by
Professor Alexei A. Efros. His research interests are in computer vision,
deep learning, machine learning, and graphics. He graduated summa cum laude
with BS and MEng degrees from Cornell University in ECE in 2010. He is a
recipient of the 2017 Adobe Research Fellowship.

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

-- 
*Alicia McClarin*
*Toyota Technological Institute at Chicago*
*6045 S. Kenwood Ave., **Office 518*
*Chicago, IL 60637*
*www.ttic.edu* <http://www.ttic.edu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20190507/953d5971/attachment-0001.html>