Open AccessEvaluating the progress of deep learning for visual relational concepts
Author(s) -
Sebastian Stabinger,
David Peer,
Justus Piater,
Antonio Jose Rodríguez-Sánchez
Publication year - 2021
Publication title -
journal of vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.126
H-Index - 113
ISSN - 1534-7362
DOI - 10.1167/jov.21.11.8
Subject(s) - computer science , artificial intelligence , statistical relational learning , convolutional neural network , deep learning , visual reasoning , cognition , point (geometry) , machine learning , cognitive science , relational database , psychology , data mining , mathematics , geometry , neuroscience
Convolutional neural networks have become the state-of-the-art method for image classification in the last 10 years. Despite the fact that they achieve superhuman classification accuracy on many popular datasets, they often perform much worse on more abstract image classification tasks. We will show that these difficult tasks are linked to relational concepts from cognitive psychology and that despite progress over the last few years, such relational reasoning tasks still remain difficult for current neural network architectures. We will review deep learning research that is linked to relational concept learning, even if it was not originally presented from this angle. Reviewing the current literature, we will argue that some form of attention will be an important component of future systems to solve relational tasks. In addition, we will point out the shortcomings of currently used datasets, and we will recommend steps to make future datasets more relevant for testing systems on relational reasoning.