Sorry, you need to enable JavaScript to visit this website.

Error message

  • The specified file temporary://fileP79uVm could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://fileOF6mEv could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://filefgYasx could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://fileqhFVNt could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://filena7gnr could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://filejNdXDA could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://file6IVT5h could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.
  • The specified file temporary://fileMTBfJj could not be copied, because the destination directory is not properly configured. This may be caused by a problem with file or directory permissions. More information is available in the system log.

Differential Convolution Feature Guided Deep Multi-Scale Multiple Instance Learning for Aerial Scene Classification

Aerial image classification is challenging for current deep learning models due to the varied geo-spatial object scales and the complicated scene spatial arrangement. Thus, it is necessary to stress the key local feature response from a variety of scales so as to represent discriminative convolutional features. In this paper, we propose a deep multi-scale multiple instance learning (DMSMIL) framework to tackle the above challenges. Firstly, we develop a differential multi-scale dilated convolution feature extractor to exploit the different patterns from different scales.

Categories:
Pattern recognition and classification (MLR-PATT)
21 Views