Exploring Multi-Level Attention and Semantic Relationship for Remote Sensing Image Captioning

Remote sensing image captioning, which aims to understand high-level semantic information and interactions of different ground objects, is a new emerging research topic in recent years. Though image captioning has developed rapidly with convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the image captioning task for remote sensing images still suffers from two main limitations. One limitation is that the scales of objects in remote sensing images vary dramatically, which makes it difficult to obtain an effective image representation. Another limitation is that the visual relationship in remote sensing images is still underused, which should have great potential to improve the final performance. In order to deal with these two limitations, an effective framework for captioning the remote sensing image is proposed in this paper. The framework is based on multi-level attention and multi-label attribute graph convolution. Specifically, the proposed multi-level attention module can adaptively focus not only on specific spatial features, but also on features of specific scales. Moreover, the designed attribute graph convolution module can employ the attribute-graph to learn more effective attribute features for image captioning. Extensive experiments are conducted and the proposed method achieves superior performance on UCM-captions, Sydney-captions and RSICD dataset.