Cotton leaf segmentation with composite backbone architecture combining convolution and attention

Abstract

Plant leaf segmentation, especially leaf edge accurate recognition, is the data support for automatically measuring plant phenotypic parameters. However, adjusting the backbone in the current cutting-edge segmentation model for cotton leaf segmentation applications requires various trial and error costs (e.g., expert experience and computing costs). Thus, a simple and effective semantic segmentation architecture (our model) based on the composite backbone was proposed, considering the computational requirements of the mainstream Transformer backbone integrating attention mechanism. The composite backbone was composed of CoAtNet and Xception. CoAtNet integrated the attention mechanism of the Transformers into the convolution operation. The experimental results showed that our model outperformed the benchmark segmentation models PSPNet, DANet, CPNet, and DeepLab v3+ on the cotton leaf dataset, especially on the leaf edge segmentation (MIoU: 0.940, BIoU: 0.608). The composite backbone of our model integrated the convolution of the convolutional neural networks and the attention of the Transformers, which alleviated the computing power requirements of the Transformers under excellent performance. Our model reduces the trial and error cost of adjusting the segmentation model architecture for specific agricultural applications and provides a potential scheme for high-throughput phenotypic feature detection of plants.