论文成果
Hyperspectral Image Classification Based on Deep Deconvolution Network With Skip Architecture
  • 点击次数:
  • 论文类型:期刊论文
  • 发表时间:2018-08-01
  • 发表刊物:IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
  • 收录刊物:SCIE
  • 文献类型:J
  • 卷号:56
  • 期号:8
  • 页面范围:4781-4791
  • ISSN号:0196-2892
  • 关键字:Convolution neural network (CNN); deconvolution network; feature learning; hyperspectral image classification
  • 摘要:Convolution neural network (CNN) utilizes alternating convolutional and pooling layers to learn representative spatial information when the training samples are sufficient. However, for pixelwise classification of hyperspectral image, some important information is neglected by CNN, such as the erased information by the pooling operation and the appearance information from lower layers. Moreover, the lack of training samples is a common situation in remote sensing area, which afflicts CNN with overfitting problem. To address the aforementioned issues, this paper designs an end-to-end deconvolution network with skip architecture to learn the spectral-spatial features. The proposed network starts with two branches, i.e., the spatial branch and spectral branch. In the spatial branch, a band selection layer is designed to reduce parameters and remit the overfitting problem, unpooling and deconvolution operations are utilized to recover the erased information of the pooling layers and learn pixelwise spatial representation hierarchically, and the skip architecture is constructed for merging the deep semantic information with the shallow appearance information. In the spectral branch, a contextual deep network is employed for learning deep spectral features. Experimental results on three benchmark data sets reveal the competitive performance of the proposed approach over several related methods.

上一条: Deep gated attention networks for large-scale street-level scene segmentation

下一条: Information-Compensated Downsampling for Image Super-Resolution