C$^3$DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories

TL;DR

This paper introduces C$^3$DG, a novel hyperspectral imagery classification method that leverages spectral information and theoretical guarantees for convergence and error control, addressing spectral similarity challenges.

Contribution

It proposes the CRIB structure and provides new theoretical analyses for model convergence and generalization error bounds in hyperspectral image classification.

Findings

C$^3$DG outperforms existing methods on benchmark datasets.

Theoretical guarantees ensure model convergence and error bounds.

Spectral information alone effectively addresses hyperspectral-monospectra issues.

Abstract

Hyperspectral imagery (HSI) classification may suffer the challenge of hyperspectral-monospectra, where different classes present similar spectra. Joint spatial-spectral feature extraction is a popular solution for the problem, but this strategy tends to inflate accuracy since test pixels may exist in training patches. Domain generalization methods show promising potential, but they still fail to distinguish similar spectra across varying domains, in addition, the theoretical support is usually ignored. In this paper, we only rely on spectral information to solve the hyperspectral-monospectra problem, and propose a Convergence and Error-Constrained Conditional Domain Generalization method for Hyperspectral Imagery Classification (C$^3$DG). The major contributions of this paper include two aspects: the Conditional Revising Inference Block (CRIB), and the corresponding theories for model convergence and generalization errors. CRIB is the kernel structure of the proposed method, which employs a shared encoder and multi-branch decoders to fully leverage the conditional distribution during training, achieving a decoupling that aligns with the generation mechanisms of HSI. Moreover, to ensure model convergence and maintain controllable error, we propose the optimization convergence theorem and risk upper bound theorem. In the optimization convergence theorem, we ensure the model convergence by demonstrating that the gradients of the loss terms are not contradictory. In the risk upper bound theorem, our theoretical analysis explores the relationship between test-time training and recent related work to establish a concrete bound for error. Experimental results on three benchmark datasets indicate the superiority of C$^3$DG.