[Colloquium] Xiao Zhang MS Presentation/May 12, 2023

[Megan Woodward]

This is an announcement of Xiao Zhang's MS Presentation
===============================================
Candidate: Xiao Zhang

Date: Friday, May 12, 2023

Time: 10 am CST

Location: JCL 298

M.S. Paper Title: Self-Supervised visual representation learning

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.
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.

Advisors: Michael Maire

Committee Members: Michael Maire, Rebecca Willett, and Greg Shakhnarovich

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20230428/c314b61e/attachment.html>