all AI news
Does SAM dream of EIG? Characterizing Interactive Segmenter Performance using Expected Information Gain
April 26, 2024, 4:42 a.m. | Kuan-I Chung, Daniel Moyer
cs.LG updates on arXiv.org arxiv.org
Abstract: We introduce an assessment procedure for interactive segmentation models. Based on concepts from Bayesian Experimental Design, the procedure measures a model's understanding of point prompts and their correspondence with the desired segmentation mask. We show that Oracle Dice index measurements are insensitive or even misleading in measuring this property. We demonstrate the use of the proposed procedure on three interactive segmentation models and subsets of two large image segmentation datasets.
abstract arxiv assessment bayesian concepts cs.cv cs.it cs.lg design dice experimental index information interactive math.it oracle performance prompts sam segmentation show type understanding
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US