3 papers
cs.CV2024
Successes and Limitations of Object-centric Models at Compositional Generalisation
Milton L. Montero, Jeffrey S. Bowers, Gaurav Malhotra
In recent years, it has been shown empirically that standard disentangled latent variable models do not support robust compositional learning in the visual domain. Indeed, in spite…
cs.CV2024
MindSet: Vision. A toolbox for testing DNNs on key psychological experiments
Valerio Biscione, Milton L. Montero, Marin Dujmovic +9
Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the…
cs.CV2024
Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach
Guillermo Puebla, Jeffrey S. Bowers
Achieving visual reasoning is a long-term goal of artificial intelligence. In the last decade, several studies have applied deep neural networks (DNNs) to the task of learning visu…