all AI news
PRIME: Prioritizing Interpretability in Failure Mode Extraction
March 15, 2024, 4:46 a.m. | Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi
cs.CV updates on arXiv.org arxiv.org
Abstract: In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by first identifying clusters (or directions) of incorrectly classified samples in a latent space and then aiming to provide human-understandable text descriptions for them. We observe that in some cases, describing text does not match well with identified failure modes, partially owing to the fact that shared interpretable attributes of failure …
abstract arxiv challenge classification cs.cv extraction failure human image interpretability prime samples space study text them type work
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
1 day, 18 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Director, Clinical Data Science
@ Aura | Remote USA
Research Scientist, AI (PhD)
@ Meta | Menlo Park, CA | New York City