DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

Abstract

Traditional hyperspectral image semantic segmentation algorithms can not fully utilize the spatial information or realize efficient segmentation with less sample data. In order to solve the above problems, a U-shaped hyperspectral semantic segmentation model (DCCaps-UNet) based on the depthwise separable and conditional convolution capsule network was proposed in this study. The whole network is an encoding–decoding structure. In the encoding part, image features are firstly fully extracted and fused. In the decoding part, images are then reconstructed by upsampling. In the encoding part, a dilated convolutional capsule block is proposed to fully acquire spatial information and deep features and reduce the calculation cost of dynamic routes using a conditional sliding window. A depthwise separable block is constructed to replace the common convolution layer in the traditional capsule network and efficiently reduce network parameters. After principal component analysis (PCA) dimension reduction and patch preprocessing, the proposed model was experimentally tested with Indian Pines and Pavia University public hyperspectral image datasets. The obtained segmentation results of various ground objects were analyzed and compared with those obtained with other semantic segmentation models. The proposed model performed better than other semantic segmentation methods and achieved higher segmentation accuracy with the same samples. Dice coefficients reached 0.9989 and 0.9999. The OA value can reach 99.92% and 100%, respectively, thus, verifying the effectiveness of the proposed model.

SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images

“…Associated with PCA, PSE-UNet introduces cumulative variance contribution rate (CVCR) as a new metric for PCA-based dimensionality reduction. Taking advantage of the stable performance of U-Net architecture, Wei et al proposed the DCCaps-UNet, a novel U-shaped hyperspectral image semantic segmentation model that leverages depthwise separable and conditional convolution capsule networks to enhance spatial information utilization and segmentation efficiency with fewer samples [45]. Although these designs effectively capture multi-scale features and enhance results through post-processing, they do not yet achieve optimal pixel-wise semantic inference due to limitations in contextual understanding.…”