Cohere For AI - Guest Speaker: Gowthami Somepalli, Ph.D candidate

About the session: This session will cover the following papers:

1. https://arxiv.org/abs/2212.03860 (CVPR'23)
2. https://arxiv.org/abs/2305.20086 (Neurips'23
3. https://arxiv.org/abs/2404.01292 (Freshly baked)

Cutting-edge diffusion models produce high-quality and customizable images, enabling their use for commercial art and graphic design purposes. First, I will discuss our study of various frameworks to detect replication. Then, I will show how we used these frameworks to identify memorization in the Stable Diffusion 1.4 model. In the second part, I will discuss various factors contributing to memorization in diffusion models. While it is widely believed that duplicated images in the training set are responsible for content replication at inference time, I will show results on how the text conditioning of the model also plays an important role. I will discuss several techniques we proposed based on these findings for reducing data replication in both training and inference times. Lastly, I will discuss my recent work on understanding style memorization in diffusion models where we propose a feature extractor for representing style, which we then use to detect style in Stable Diffusion generated images.

About the speaker: Gowthami Somepalli is a Ph.D. candidate in the Department of Computer Science at the University of Maryland, College Park. The focus of her research lies at the intersection of Machine Learning (ML) and Computer Vision with the aim of building practical ML systems that are interpretable and robust. Her recent works range from developing novel deep learning architectures and training methodologies for diverse domains such as tables, images, and language, to building tools to explain and analyze the success/failure modes of common deep learning models. Before starting her Ph.D., she worked in industry in various product and engineering roles and received her bachelor's from IIT Madras. She is also the recipient of the Kulkarni Fellowship, Amazon Research Fellowship, CVPR Doctoral Consortium Award, and Ann-Wylie Dissertation Fellowship.

Add event to calendar

Apple Google Office 365 Outlook Outlook.com Yahoo