Progressive Scale-aware Network for Remote sensing Image Change Captioning
This work addresses the problem of generating accurate captions for changes in complex remote sensing scenes, which is incremental as it builds on existing methods by improving multi-scale feature extraction and utilization.
The paper tackles the challenge of identifying and describing visual changes in remote sensing images with objects at different scales by proposing a progressive scale-aware network (PSNet), which outperforms previous methods in remote sensing image change captioning.
Remote sensing (RS) images contain numerous objects of different scales, which poses significant challenges for the RS image change captioning (RSICC) task to identify visual changes of interest in complex scenes and describe them via language. However, current methods still have some weaknesses in sufficiently extracting and utilizing multi-scale information. In this paper, we propose a progressive scale-aware network (PSNet) to address the problem. PSNet is a pure Transformer-based model. To sufficiently extract multi-scale visual features, multiple progressive difference perception (PDP) layers are stacked to progressively exploit the differencing features of bitemporal features. To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers. Experiments show that the PDP layer and SR module are effective and our PSNet outperforms previous methods. Our code is public at https://github.com/Chen-Yang-Liu/PSNet