Hierarchical Attention Networks for Image Classification of Remote Sensing Images Based on Visual Q&A Methods

Haochen Li , Tian Wang (1) , Mengyi Zhang (2) , Aichun Zhu (3) , Guangcun Shan (4) , Hichem Snoussi (3)

1 School of Automation and Electrical Engineering [Beijing] (University of Science and Technology Beijing)
2 NJUST - Nanjing University of Science and Technology
3 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
4 School of Instrumentation Science and Opto-electronics Engineering [Beijing]

This paper provides a mixed attention network for remote sensing image classification whose idea comes from VQA methods. In this way, it could deal with more complex requests beyond just identifying what is in the picture. The HAN (Hierarchial Attention Network) consists of an attention model to detect details on one hand and a self-attention model to detect global information on the other hand. Through attention heat maps we could see division of work is really effective and the HAN has a great performance on NWPU-RESISC45 data set. Furthermore, we may add some other subnetworks to reinforce this ability in the future.

Domaines: Automatique / Robotique

Haochen Li, Tian Wang, Mengyi Zhang, Aichun Zhu, Guangcun Shan, et al.. Hierarchical Attention Networks for Image Classification of Remote Sensing Images Based on Visual Q&A Methods. 2019 Chinese Automation Congress (CAC), Nov 2019, Hangzhou, China. pp.4712-4717, ⟨10.1109/CAC48633.2019.8997347⟩. ⟨hal-02486750⟩