Abstract:
Convolutional neural networks (CNNs) can extract shift-invariant features and have been widely applied in the change detection task. However, common CNN lacks noise robus...Show MoreMetadata
Abstract:
Convolutional neural networks (CNNs) can extract shift-invariant features and have been widely applied in the change detection task. However, common CNN lacks noise robustness and needs supervised data to alleviate these problems; in this article, we propose a novel deep shearlet convolutional neural network (ShearNet) for change detection in synthetic aperture radar (SAR) images. In the network, a shearlet denoising layer (SDL) is designed to enhance the representation ability of common CNN. In SDL, feature maps are decomposed into subband coefficients by shearlet transform (ST). Due to the optimal sparse representation property and high direction sensitivity of ST, the network can capture important geometric information. Then, hard-threshold shrinkage is applied to high-frequency subbands to drop small coefficients that are most likely to be noise so that reducing the effect of noise. Finally, ShearNet is trained by introducing a noise-robust loss with noisy labels. The noisy labels are obtained by deep clustering that shows more robustness than existing preclassification methods. This fine-tuning process novelly follows the paradigm of learning from noisy labels to aside the difficulty of precisely labeling samples. Our experimental results on multiple real SAR datasets show that ShearNet can boost accuracy and have better applicability for change detection in SAR images. The source code is available at https://github.com/yizhilanmaodhh/ShearNet.
Published in: IEEE Transactions on Geoscience and Remote Sensing ( Volume: 60)