ImagenHub: Standardizing the evaluation of conditional image generation models

Authors: M Ku, T Li, K Zhang, Y Lu, X Fu, W Zhuang

Published: 2024

Publication: - arXiv preprint arXiv …, 2023 - arxiv.org

This paper presents a method for **aligning machine vision model representations with human visual similarity judgments across different abstraction levels, improving how well models reflect human perceptual and conceptual organization and enhancing generalization and uncertainty prediction.

Institution: University of Waterloo, Ohio State University, University of California Santa Barbara, University of Pensylvania

Research Area: AI alignment, Representation learning, Cognitive computational modeling, Vision foundation models evaluation, Multimodal, Vision models

Discipline: Computer Science, Artificial Intelligence, Machine Learning

Citations: 59

DOI: https://doi.org/10.48550/arXiv.2310.01596