LiCa: Label-Indicate-Conditional-Alignment Domain Generalization for Pixel-Wise Hyperspectral Imagery Classification

One of the major difficulties for hyperspectral imagery (HSI) classification is the hyperspectral heterospectra, which refers to the same material presenting different spectra. Although joint spatial-spectral classification methods can relieve this problem, they may lead to falsely high accuracy because the test samples may be involved during the training process. How to address the hyperspectral-heterospectra problem remains a great challenge for pixel-wise HSI classification methods. Domain generalization is a promising technique that may contribute to the heterospectra problem, where the different spectra of the same material can be considered as several domains. In this article, inspired by the theory of domain generalization, we provide a formulaic expression for hyperspectral heterospectra. To be specific, we consider the spectra of one material as a conditional distribution and propose a domain-generalization-based method for pixel-wise HSI classification. The key of our proposed method is a new label-indicate-conditional-alignment (LiCa) block that focuses on aligning the spectral conditional distributions of different domains. In the LiCa block, we define two loss functions-cross-domain conditional alignment and cross-domain entropy (CdE)-to describe the heterogeneity of HSI. Moreover, we have provided the theoretical foundation for the newly proposed loss functions, by analyzing the upper bound of classification error in any target domains. Experiments on several public datasets indicate that the LiCa block has achieved better generalization performance when compared with other pixel-wise classification methods.

Automated summary

This article introduces a domain generalization technique to address the problem of hyperspectral heterospectra in pixel-wise classification. The proposed LiCa block aligns the spectral conditional distributions of different domains to achieve better generalization performance.