Aligning machine and human visual representations across abstraction levels

Authors: L Muttenthaler, K Greff, F Born, B Spitzer, S Kornblith

Published: 2025

Publication: Nature, 2025 - nature.com

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: Google DeepMind, Google, Machine Learning Group, Technische Universität Berlin, BIFOLD, Berlin Institute for the Foundations of Learning and Data, Max Planck Institute

Research Area: Cognitive Alignment, Computer Vision, Multi-level Conceptual Knowledge

Discipline: Artificial Intelligence, Cognitive Science

Citations: 11