MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
This work addresses land resource management and yield estimation through improved segmentation accuracy, but it is incremental as it builds on the widely used U-Net architecture.
The paper tackled semantic segmentation of fine-resolution remotely sensed images by proposing MACU-Net, which incorporates multi-scale skip connections and asymmetric convolutions into U-Net, achieving superior performance over benchmarks like U-Net and U-Net 3+ on two datasets.
Semantic segmentation of remotely sensed images plays an important role in land resource management, yield estimation, and economic assessment. U-Net, a deep encoder-decoder architecture, has been used frequently for image segmentation with high accuracy. In this Letter, we incorporate multi-scale features generated by different layers of U-Net and design a multi-scale skip connected and asymmetric-convolution-based U-Net (MACU-Net), for segmentation using fine-resolution remotely sensed images. Our design has the following advantages: (1) The multi-scale skip connections combine and realign semantic features contained in both low-level and high-level feature maps; (2) the asymmetric convolution block strengthens the feature representation and feature extraction capability of a standard convolution layer. Experiments conducted on two remotely sensed datasets captured by different satellite sensors demonstrate that the proposed MACU-Net transcends the U-Net, U-NetPPL, U-Net 3+, amongst other benchmark approaches. Code is available at https://github.com/lironui/MACU-Net.