One-Shot Learning in Discriminative Neural Networks
This addresses the problem of data-efficient learning for computer vision practitioners, but it is incremental as it builds on existing convnet architectures and Bayesian approaches.
The paper tackles one-shot learning of visual categories by proposing a Bayesian procedure to update a pretrained convnet for novel image classification with limited data, achieving competitive performance with state-of-the-art methods.
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.