Registration is open until 06 June 2024 11:00 AM

Abstract:

Generative Adversarial Networks (GANs) are a branch of generative models that offer exceptional capability in generating realistic images, audio, video, and various data forms. The first talk will provide a perspective on the utility of scene synthesis for training machine learning models. The second talk will focus on the recent advancements in GANs. Neural Architecture Search (NAS) aims to automate the search for an optimal architecture that meets specific performance criteria, significantly reducing the manual effort involved in model design. The recent surge in network compression underscores the necessity to make these powerful models more accessible and efficient, particularly for resource-constrained environments. This talk presents a new training procedure that leverages NAS to discover the optimal architecture for image generation while employing the Maximum Mean Discrepancy (MMD) repulsive loss for adversarial training. Moreover, the generator network is compressed using tensor decomposition to reduce its computational footprint and inference time while preserving its generative performance and allowing it to be deployed on edge devices.

Location

UAlbany ETEC: Location is 1400 Washington Avenue, Albany, NY 12222 , Rm 340 (Ops Command Center)
Virtual: Join WebEx meeting.

Speakers

Dr. Raghuveer Rao is the Chief of the Intelligent Perception Branch at the DEVCOM Army Research Laboratory (ARL) in Adelphi, Maryland, where he oversees R&D in multimodal computer vision and applications, mainly to autonomous systems and scene understanding. Prior to joining ARL, Dr. Rao was a professor of electrical engineering and imaging science at the Rochester Institute of Technology. He has also held visiting appointments with the Indian Institute of Science, the US Air Force Research Laboratory, the US Naval Surface Warfare Center, and Princeton University. He has made multiple research contributions to signal & image processing, communication, and computer vision, and serves as an ABET program evaluator for electrical engineering. Dr. Rao is a life fellow of IEEE and an elected fellow of SPIE.
Prasanna Reddy Pulakurthi is a Ph.D. candidate in the Electrical and Computer Engineering department at Rochester Institute of Technology (RIT). His primary research areas include Generative AI, Computer Vision, Machine Learning, and Deep Learning. He is particularly interested in the development and refinement of image generation, human action recognition, and image translation models.
Dr. Sohail A. Dianat received a B.S. degree in Electrical Engineering from the Arya-Mehr University of Technology in Tehran, Iran, and his M.S. and D.Sc. degrees in Electrical Engineering from George Washington University. In September 1981, he joined the Rochester Institute of Technology, where he is currently a professor of Electrical Engineering and Imaging Science. Dr. Dianat’s current research interests include digital signal/image processing and wireless communication.

The flyer may be downloaded here.