Attentive Recurrent Comparators

• Main Authors: Shyam, Pranav, Gupta, Shubham, Dukkipati, Ambedkar
• Format: Journal Article
• Language: English
• Published: 02-03-2017
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.1703.00767

Rapid learning requires flexible representations to quickly adopt to new
evidence. We develop a novel class of models called Attentive Recurrent
Comparators (ARCs) that form representations of objects by cycling through them
and making observations. Using the representations extracted by ARCs, we
develop a way of approximating a \textit{dynamic representation space} and use
it for one-shot learning. In the task of one-shot classification on the
Omniglot dataset, we achieve the state of the art performance with an error
rate of 1.5\%. This represents the first super-human result achieved for this
task with a generic model that uses only pixel information.