Instance-aware Remote Sensing Image Captioning with Cross-hierarchy Attention

TL;DR

This paper introduces an instance-aware, cross-hierarchy attention mechanism for remote sensing image captioning, enabling dynamic focus on multi-level semantic information and tiny objects, improving captioning accuracy.

Contribution

It proposes a novel multi-level feature architecture combined with cross-hierarchy attention for improved remote sensing image captioning.

Findings

Outperforms existing methods on public datasets.

Effectively captures tiny objects and multi-level semantics.

Enhances image understanding in diverse remote sensing images.

Abstract

The spatial attention is a straightforward approach to enhance the performance for remote sensing image captioning. However, conventional spatial attention approaches consider only the attention distribution on one fixed coarse grid, resulting in the semantics of tiny objects can be easily ignored or disturbed during the visual feature extraction. Worse still, the fixed semantic level of conventional spatial attention limits the image understanding in different levels and perspectives, which is critical for tackling the huge diversity in remote sensing images. To address these issues, we propose a remote sensing image caption generator with instance-awareness and cross-hierarchy attention. 1) The instances awareness is achieved by introducing a multi-level feature architecture that contains the visual information of multi-level instance-possible regions and their surroundings. 2) Moreover, based on this multi-level feature extraction, a cross-hierarchy attention mechanism is proposed to prompt the decoder to dynamically focus on different semantic hierarchies and instances at each time step. The experimental results on public datasets demonstrate the superiority of proposed approach over existing methods.