skip to main content
Idioma:

RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification

Zhang, Zhen ; Liu, Shanghao ; Zhang, Yang ; Chen, Wenbo

Remote sensing (Basel, Switzerland), 2022-01, Vol.14 (1), p.141 [Periódico revisado por pares]

Basel: MDPI AG

Texto completo disponível

Citações Citado por
  • Título:
    RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification
  • Autor: Zhang, Zhen ; Liu, Shanghao ; Zhang, Yang ; Chen, Wenbo
  • Assuntos: Accuracy ; Artificial neural networks ; Classification ; Computer architecture ; convolutional neural networks (CNNs) ; Datasets ; Deep learning ; Image classification ; Machine learning ; Methods ; neural architecture search (NAS) ; Neural networks ; Redundancy ; Remote sensing ; remote sensing image scene classification ; Search methods ; Semantics
  • É parte de: Remote sensing (Basel, Switzerland), 2022-01, Vol.14 (1), p.141
  • Descrição: 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.
  • Editor: Basel: MDPI AG
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  5 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.