Research talk

Enhanced zero-shot image classification with LLM assistance

May 31, 2024

12:00 pm - 1:00 pm Pacific Time

Register now

By submitting this form, I agree to the Terms of Use and acknowledge that my information will be used in accordance with the Privacy Policy.

During this research talk, you’ll see how follow-up differential descriptions (FuDD) can enhance zero-shot image classification by tailoring class descriptions for each dataset.

PhD Student Reza Esfandiarpoor from Brown University will discuss how FuDD identifies ambiguous classes for each image and then employs a large language model (LLM) to produce new descriptions that better distinguish them.

The talk will address:

  • How FuDD performs compared to few-shot adaptation methods.
  • What challenges FuDD performs well on.
  • How to use FuDD in your workflow.

Speakers

Image

Reza Esfandiarpoor

PhD Student
Brown University

Reza Esfandiarpoor is a fifth-year Ph.D. candidate in the Department of Computer Science at Brown University, advised by Stephen Bach. His research interests concern machine learning systems with multiple large pre-trained models and the new challenges and opportunities that interactions between these models provide.