A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection
This work addresses efficiency issues for change detection in SAR images, enabling deployment on edge devices, but it is incremental as it builds on existing CNN methods with optimizations.
The authors tackled the problem of heavy computational and memory requirements in existing Convolutional Neural Networks for bitemporal SAR image change detection by proposing a lightweight network, which achieved better performance and generalization on four datasets, especially in complex scenes.
Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation. Motivated by this, in this paper, we propose a lightweight neural network to reduce the computational and spatial complexity and facilitate the change detection on an edge device. In the proposed network, we replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. Next, we employ dilated convolutional kernels with a few non-zero entries that reduce the running time in convolutional operators. Comparing with the conventional convolutional neural network, our light-weighted neural network will be more efficient with fewer parameters. We verify our light-weighted neural network on four sets of bitemporal SAR images. The experimental results show that the proposed network can obtain better performance than the conventional CNN and has better model generalization, especially on the challenging datasets with complex scenes.