Denoising-Based Multiscale Feature Fusion for Remote Sensing Image Captioning

Benefiting from deep learning technology, it becomes achievable to generate captions for remote sensing images and great progress has been made in the recent years. However, the large scale variation of remote sensing images, which would lead to errors or omissions in feature extraction, still limits the further improvement of caption quality. To address this problem, we propose a denoising based multi-scale feature fusion (DMSFF) mechanism for remote sensing image captioning in this paper. The proposed DMSFF mechanism aggregates multiscale features with the denoising operation at the stage of visual feature extraction. It can help the encoder-decoder framework, which is widely used in image captioning, to obtain the denoising multi-scale feature representation. In experiments, we apply the proposed DMSFF in the encoder-decoder framework and perform the comparative experiments on two public remote sensing image captioning data sets including UCM-captions and Sydneycaptions. The experimental results demonstrate the effectiveness of our method.