English

One-Shot Learning in Discriminative Neural Networks

Machine Learning 2017-07-19 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1707.05562,
  title  = {One-Shot Learning in Discriminative Neural Networks},
  author = {Jordan Burgess and James Robert Lloyd and Zoubin Ghahramani},
  journal= {arXiv preprint arXiv:1707.05562},
  year   = {2017}
}

Comments

3 pages, 3 figures

R2 v1 2026-06-22T20:50:09.920Z