Memory Matching Networks for One-Shot Image Recognition

TL;DR

This paper introduces Memory Matching Networks (MM-Net), a novel deep learning architecture that enhances one-shot image recognition by integrating memory modules and learning to adapt network parameters on the fly, achieving state-of-the-art results.

Contribution

The paper presents MM-Net, which uniquely combines memory and learning to learn for one-shot recognition, allowing a unified model for varying shots and categories.

Findings

Achieves 99.28% accuracy on Omniglot

Improves miniImageNet accuracy from 49.21% to 53.37%

Outperforms existing one-shot learning methods

Abstract

In this paper, we introduce the new ideas of augmenting Convolutional Neural Networks (CNNs) with Memory and learning to learn the network parameters for the unlabelled images on the fly in one-shot learning. Specifically, we present Memory Matching Networks (MM-Net) --- a novel deep architecture that explores the training procedure, following the philosophy that training and test conditions must match. Technically, MM-Net writes the features of a set of labelled images (support set) into memory and reads from memory when performing inference to holistically leverage the knowledge in the set. Meanwhile, a Contextual Learner employs the memory slots in a sequential manner to predict the parameters of CNNs for unlabelled images. The whole architecture is trained by once showing only a few examples per class and switching the learning from minibatch to minibatch, which is tailored for one-shot learning when presented with a few examples of new categories at test time. Unlike the conventional one-shot learning approaches, our MM-Net could output one unified model irrespective of the number of shots and categories. Extensive experiments are conducted on two public datasets, i.e., Omniglot and \emph{mini}ImageNet, and superior results are reported when compared to state-of-the-art approaches. More remarkably, our MM-Net improves one-shot accuracy on Omniglot from 98.95% to 99.28% and from 49.21% to 53.37% on \emph{mini}ImageNet.