A Novel Deep Nearest Neighbor Neural Network for Few-Shot Remote Sensing Image Scene Classification

Remote sensing image scene classification has become more and more popular in recent years. As we all know, it is very difficult and time-consuming to obtain a large number of manually labeled remote sensing images. Therefore, few-shot scene classification of remote sensing images has become an urgent and important research task. Fortunately, the recently proposed deep nearest neighbor neural network (DN4) has made a breakthrough in few-shot classification. However, due to the complex background in remote sensing images, DN4 is easily affected by irrelevant local features, so DN4 cannot be directly applied in remote sensing images. For this reason, a deep nearest neighbor neural network based on attention mechanism (DN4AM) is proposed to solve the few-shot scene classification task of remote sensing images in this paper. Scene class-related attention maps are used in our method to reduce interference from scene-semantic irrelevant objects to improve the classification accuracy. Three remote sensing image datasets are used to verify the performance of our method. Compared with several state-of-the-art methods, including MatchingNet, RelationNet, MAML, Meta-SGD and DN4, our method achieves promising results in the few-shot scene classification of remote sensing images.

Automated summary

Remote sensing image scene classification has become popular, but manually labeling large amounts of remote sensing images is difficult and time-consuming. Therefore, few-shot scene classification of remote sensing images is an urgent research task. This paper proposes a deep nearest neighbor neural network based on attention mechanism (DN4AM) to solve this task. By using scene class-related attention maps to reduce interference from irrelevant objects, our method achieves promising results in few-shot scene classification of remote sensing images, outperforming several state-of-the-art methods.