One-Shot Learning in Discriminative Neural Networks
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Abstract
We consider the task of one-shot learning of visual categories. In this paper we explore a Bayesian procedure for updating a pretrained convnet to classify a novel image category for which data is limited. We decompose this convnet into a fixed feature extractor and softmax classifier. We assume that the target weights for the new task come from the same distribution as the pretrained softmax weights, which we model as a multivariate Gaussian. By using this as a prior for the new weights, we demonstrate competitive performance with state-of-the-art methods whilst also being consistent with 'normal' methods for training deep networks on large data.
Description
Keywords
stat.ML, stat.ML, cs.LG
Journal Title
CoRR
Conference Name
Journal ISSN
Volume Title
Publisher
Publisher DOI
Publisher URL
Sponsorship
EPSRC (via University of Sheffield) (143103)