RRSIS: Referring Remote Sensing Image Segmentation
This work addresses the gap in referring image segmentation for remote sensing imagery, which is incremental as it adapts existing techniques to a new domain with potential real-world applications.
The paper introduces referring remote sensing image segmentation (RRSIS) to localize objects based on expressions in remote sensing images, creating a new dataset (RefSegRS) and proposing a language-guided cross-scale enhancement (LGCE) module that improves performance over existing methods, though specific numerical gains are not detailed.
Localizing desired objects from remote sensing images is of great use in practical applications. Referring image segmentation, which aims at segmenting out the objects to which a given expression refers, has been extensively studied in natural images. However, almost no research attention is given to this task of remote sensing imagery. Considering its potential for real-world applications, in this paper, we introduce referring remote sensing image segmentation (RRSIS) to fill in this gap and make some insightful explorations. Specifically, we create a new dataset, called RefSegRS, for this task, enabling us to evaluate different methods. Afterward, we benchmark referring image segmentation methods of natural images on the RefSegRS dataset and find that these models show limited efficacy in detecting small and scattered objects. To alleviate this issue, we propose a language-guided cross-scale enhancement (LGCE) module that utilizes linguistic features to adaptively enhance multi-scale visual features by integrating both deep and shallow features. The proposed dataset, benchmarking results, and the designed LGCE module provide insights into the design of a better RRSIS model. We will make our dataset and code publicly available.