<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">This is an announcement of Xiao Zhang's MS Presentation</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">===============================================</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Candidate: Xiao Zhang</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Date: Friday, May 12, 2023</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Time: 10 am CST</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Location: JCL 298</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">M.S. Paper Title: Self-Supervised visual representation learning</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">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="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">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="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Advisors: Michael Maire</span><br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<br style="box-sizing: content-box; color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px;" class="">
<span style="color: rgb(33, 33, 33); font-family: Roboto, Helvetica, Arial, sans-serif; font-size: 14.666667px; background-color: rgb(255, 255, 255);" class="">Committee Members: Michael Maire, Rebecca Willett, and Greg Shakhnarovich</span><br class="">
<br class="">
</body>
</html>