MLLGJul 18, 2017

One-Shot Learning in Discriminative Neural Networks

arXiv:1707.05562v111 citations
Originality Incremental advance
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes