pith. sign in

arxiv: 1707.05562 · v1 · pith:LDQSVU5Nnew · submitted 2017-07-18 · 📊 stat.ML · cs.LG

One-Shot Learning in Discriminative Neural Networks

classification 📊 stat.ML cs.LG
keywords weightsconvnetdatalearningmethodsnetworksone-shotpretrained
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.