<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body>
<div dir="ltr">
<div style=""></div>
<div style="">
<div dir="ltr"><span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">This is an announcement of Xiao Zhang's
MS Presentation</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">===============================================</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Candidate: Xiao Zhang</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Date: Friday, May 12, 2023</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Time: 10 am CST</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Location: JCL 298</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">M.S. Paper Title: Self-Supervised visual representation
learning</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Abstract: In this talk, I will discuss my research on self-supervised
visual representation learning, which consists of two parts. The primary focus of the talk will be on the first part, where we propose a framework for learning visual representation from hierarchical grouping. We operationalize grouping via a contour detector
that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically
predict hierarchical region structure. These predictions guide self-supervised contrastive feature learning: we task a deep network with producing per-pixel embeddings whose pairwise distances respect the region hierarchy. Experiments demonstrate that our
approach can serve as state-of-the-art generic pretraining, benefiting downstream tasks. We additionally explore applications for semantic region search and video-based object instance tracking. </span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">In the second part of my presentation, I will discuss two
recent works on learning visual representation from a generative model. The first work employs the generative adversarial network for feature learning, utilizing proposed structural adversarial objectives. The second work involves extracting dense representation
from a denoising autoencoder using layer-distributed spectral clustering.</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Advisors: Michael Maire</span><br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<br style="text-decoration: none; box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;">
<span style="text-decoration: none; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255); display: inline !important;">Committee Members: Michael Maire, Rebecca Willett, and
Greg Shakhnarovich</span><br>
</div>
</div>
</div>
</body>
</html>