VIDEO DOI: https://doi.org/10.48448/97sr-ed82

poster

NAACL 2022

July 12, 2022

Seattle, United States

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold

Please log in to leave a comment

Downloads

SlidesPaperTranscript English (automatic)

Next from NAACL 2022

poster

Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

NAACL 2022

Sanghwan Bae

12 July 2022

Similar lecture

poster

Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation

COLING 2022

Yanan Wu and 2 other authors

12 October 2022

Stay up to date with the latest Underline news!

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved