Transductive Mutual Information Encoder Network for Few Shot Learning

Abstract

Deep learning has made breakthroughs in recent decades and has been widely used in many domains. However, most of those methods heavily rely on large labeled datasets, which results in poor performance when provided with limited labeled data. Few-shot learning (FSL), which aims at learning a novel task with limited samples, has attracted a lot of research recently. The previous metric-based methods ignore the internal bias between the training and testing datasets since the categories of the testing dataset are completely different from the training set. Transfer learning methods also suffer from few labeled data and tends to be overfitting in this situation. This paper proposes Transductive Mutual Information Encoder Network (TMIN) for few-shot learning problems. TMIN typically trains a convolutional neural network with a mutual information maximization module in an unsupervised manner. The trained network maps images to a high dimensional embedding space. Then the embeddings are exploited to measure the similarity between samples by a distance metric. Experiments indicate that the proposed model achieves competitive performance compared with the counterparts.