Attentive Weights Generation for Few Shot Learning via Information Maximization

Yiluan Guo, Ngai-Man Cheung

TL;DR: A novel few shot learning method to generate query-specific classification weights via information maximization.

Abstract: Few shot image classification aims at learning a classifier from limited labeled data. Generating the classification weights has been applied in many meta-learning approaches for few shot image classification due to its simplicity and effectiveness. However, we argue that it is difficult to generate the exact and universal classification weights for all the diverse query samples from very few training samples. In this work, we introduce Attentive Weights Generation for few shot learning via Information Maximization (AWGIM), which addresses current issues by two novel contributions. i) AWGIM generates different classification weights for different query samples by letting each of query samples attends to the whole support set. ii) To guarantee the generated weights adaptive to different query sample, we re-formulate the problem to maximize the lower bound of mutual information between generated weights and query as well as support data. As far as we can see, this is the first attempt to unify information maximization into few shot learning. Both two contributions are proved to be effective in the extensive experiments and we show that AWGIM is able to achieve state-of-the-art performance on benchmark datasets.

Code: https://www.dropbox.com/s/gine9r9esjrwns2/AWGIM.zip?dl=0

Keywords: few shot learning, meta learning, information maximization, image classification