Explanation-Based Attention for Semi-Supervised Deep Active Learning

Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa

Keywords: active learning, attention, explanation, feature extraction

TL;DR: We introduce an attention mechanism to improve feature extraction for deep active learning (AL) in the semi-supervised setting.

Abstract: We introduce an attention mechanism to improve feature extraction for deep active learning (AL) in the semi-supervised setting. The proposed attention mechanism is based on recent methods to visually explain predictions made by DNNs. We apply the proposed explanation-based attention to MNIST and SVHN classification. The conducted experiments show accuracy improvements for the original and class-imbalanced datasets with the same number of training examples and faster long-tail convergence compared to uncertainty-based methods.