Attention Mining Branch for Optimizing Attention Map

Abstract

Attention branch networks (ABNs) can achieve high accuracy by visualizing the attention area of the network during inference and utilizing it in the recognition process. However, if the attention area does not highlight the target object to be recognized, it may cause recognition failure. While there is a method for fine-tuning the ABN using attention maps modified by human knowledge, it takes up a lot of labor and time because the attention map needs to be modified manually. In this paper, we propose a method that automatically optimizes the attention map by introducing an attention mining branch to the ABN. Our evaluation experiments show that the proposed method improves the recognition accuracy and obtains an attention map that appropriately focuses on the target object to be recognized.