Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations

While deep learning has enjoyed significant success in computer vision tasks over the past decade, many shortcomings still exist from a Cognitive Science (CogSci) perspective. In particular, the ability to subitize, i.e., quickly and accurately identify the small (less than 6) count of items, is not...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Alam, Mohammad Mahmudul, Raff, Edward, Oates, Tim
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 23.12.2023
Subjects
Artificial neural networks
Computer vision
Deep learning
Holography
Machine learning
Representations
Online AccessGet full text

Cover

More Information
Summary:While deep learning has enjoyed significant success in computer vision tasks over the past decade, many shortcomings still exist from a Cognitive Science (CogSci) perspective. In particular, the ability to subitize, i.e., quickly and accurately identify the small (less than 6) count of items, is not well learned by current Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs) when using a standard cross-entropy (CE) loss. In this paper, we demonstrate that adapting tools used in CogSci research can improve the subitizing generalization of CNNs and ViTs by developing an alternative loss function using Holographic Reduced Representations (HRRs). We investigate how this neuro-symbolic approach to learning affects the subitizing capability of CNNs and ViTs, and so we focus on specially crafted problems that isolate generalization to specific aspects of subitizing. Via saliency maps and out-of-distribution performance, we are able to empirically observe that the proposed HRR loss improves subitizing generalization though it does not completely solve the problem. In addition, we find that ViTs perform considerably worse compared to CNNs in most respects on subitizing, except on one axis where an HRR-based loss provides improvement.
ISSN:2331-8422