Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
This work addresses the challenge of few-shot object detection for remote sensing applications, where data scarcity is common, representing an incremental improvement in adapting attention mechanisms to object-level relations.
The paper tackles the problem of object detection in remote sensing images with limited labeled data by proposing a few-shot detector that leverages object-level relations through a Self-Adaptive Attention Network (SAAN), resulting in effective detection in few-shot scenes as demonstrated by experiments.
In remote sensing field, there are many applications of object detection in recent years, which demands a great number of labeled data. However, we may be faced with some cases where only limited data are available. In this paper, we proposed a few-shot object detector which is designed for detecting novel objects provided with only a few examples. Particularly, in order to fit the object detection settings, our proposed few-shot detector concentrates on the relations that lie in the level of objects instead of the full image with the assistance of Self-Adaptive Attention Network (SAAN). The SAAN can fully leverage the object-level relations through a relation GRU unit and simultaneously attach attention on object features in a self-adaptive way according to the object-level relations to avoid some situations where the additional attention is useless or even detrimental. Eventually, the detection results are produced from the features that are added with attention and thus are able to be detected simply. The experiments demonstrate the effectiveness of the proposed method in few-shot scenes.