all AI news
Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability
April 10, 2024, 4:43 a.m. | Jaehui Hwang, Junghyuk Lee, Jong-Seok Lee
cs.LG updates on arXiv.org arxiv.org
Abstract: With the advancement of generative models, the assessment of generated images becomes more and more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper, we conduct an extensive investigation into the relationship between the representation space and input space around generated images. We first propose two measures related to the presence of unnatural elements within images: complexity, which indicates how non-linear the representation space is, …
abstract advancement anomaly arxiv assessment complexity cs.cv cs.lg features generated generative generative models images investigation paper reference type vision vision models vulnerability
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