期刊
REMOTE SENSING
卷 14, 期 1, 页码 -出版社
MDPI
DOI: 10.3390/rs14010141
关键词
convolutional neural networks (CNNs); neural architecture search (NAS); remote sensing image scene classification
This article proposes a new paradigm for automatically designing a suitable CNN architecture for remote sensing scene classification. The more efficient RS-DARTS search framework is adopted to find the optimal network architecture, with new strategies introduced in the search phase, noise added to suppress skip connections, and sampling to reduce redundancy in exploring the network space. Extensive experiments demonstrate the effectiveness of the proposed method in classification performance and search cost compared to other methods.
Due to the superiority of convolutional neural networks, many deep learning methods have been used in image classification. The enormous difference between natural images and remote sensing images makes it difficult to directly utilize or modify existing CNN models for remote sensing scene classification tasks. In this article, a new paradigm is proposed that can automatically design a suitable CNN architecture for scene classification. A more efficient search framework, RS-DARTS, is adopted to find the optimal network architecture. This framework has two phases. In the search phase, some new strategies are presented, making the calculation process smoother, and better distinguishing the optimal and other operations. In addition, we added noise to suppress skip connections in order to close the gap between trained and validation processing and ensure classification accuracy. Moreover, a small part of the neural network is sampled to reduce the redundancy in exploring the network space and speed up the search processing. In the evaluation phase, the optimal cell architecture is stacked to construct the final network. Extensive experiments demonstrated the validity of the search strategy and the impressive classification performance of RS-DARTS on four public benchmark datasets. The proposed method showed more effectiveness than the manually designed CNN model and other methods of neural architecture search. Especially, in terms of search cost, RS-DARTS consumed less time than other NAS methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据