skip to main content

Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

Zhou, Weixun ; Newsam, Shawn ; Li, Congmin ; Shao, Zhenfeng

Remote sensing (Basel, Switzerland), 2017-05, Vol.9 (5), p.489 [Periódico revisado por pares]

Basel: MDPI AG

Texto completo disponível

Citações Citado por
  • Título:
    Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
  • Autor: Zhou, Weixun ; Newsam, Shawn ; Li, Congmin ; Shao, Zhenfeng
  • Assuntos: Architecture ; Aversion learning ; Complexity ; convolutional neural networks ; Datasets ; deep feature representation ; Detection ; Feature extraction ; High resolution ; Image management ; Image resolution ; Image retrieval ; Learning ; multi-layer perceptron ; Neural networks ; Remote sensing ; Representations ; Serial learning ; State of the art ; transfer learning ; Tuning
  • É parte de: Remote sensing (Basel, Switzerland), 2017-05, Vol.9 (5), p.489
  • Descrição: Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs) for high-resolution remote sensing image retrieval (HRRSIR). To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.
  • Editor: Basel: MDPI AG
  • Idioma: Inglês

Buscando em bases de dados remotas. Favor aguardar.