Unraveling the Geometry of Visual Relational Reasoning.

ABSTRACT: Humans readily generalize abstract relations, such as recognizing "constant" in shape or color, whereas neural networks struggle, limiting their flexible reasoning. To investigate mechanisms underlying such generalization, we introduce SimplifiedRPM, a novel benchmark for systematically evaluating abstract relational reasoning, addressing limitations in prior datasets. In parallel, we conduct human experiments to quantify relational difficulty, enabling direct model-human comparisons. Testing four models-ResNet-50, Vision Transformer, Wild Relation Network, and Scattering Compositional Learner (SCL)-we find that SCL generalizes best and most closely aligns with human behavior. Using a geometric approach, we identify key representation properties that accurately predict generalizatio

SUBMITTER: Shang J 

PROVIDER: S-EPMC11888560 | biostudies-literature | 2025 Jul

REPOSITORIES: biostudies-literature