MCTNet: A Multi-Scale CNN-Transformer Network for Change Detection in Optical Remote Sensing Images

Abstract

For the task of change detection (CD) in remote sensing images, deep convolution neural networks (CNNs)-based methods have recently aggregated transformer modules to improve the capability of global feature extraction. However, they suffer degraded CD performance on small changed areas due to the simple single-scale integration of deep CNNs and transformer modules. To address this issue, we propose a hybrid network based on multi-scale CNN-transformer structure, termed MCTNet, where the multi-scale global and local information are exploited to enhance the robustness of the CD performance on changed areas with different sizes. Especially, we design the ConvTrans block to adaptively aggregate global features from transformer modules and local features from CNN layers, which provides abundant global-local features with different scales. Experimental results demonstrate that our MCTNet achieves better detection performance than existing state-of-the-art CD methods.

5 pages, 3 figures

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Remote Sensing Image Change Detection with Transformers
• DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
• UNeXt: MLP-based Rapid Medical Image Segmentation Network