Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification

TL;DR

This paper introduces SDEnet, a novel domain expansion network that uses generative adversarial and contrastive learning to improve cross-scene hyperspectral image classification without target domain training.

Contribution

The paper proposes a single-source domain expansion network utilizing generative adversarial and contrastive learning for effective cross-scene HSI classification.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effective domain expansion with spectral and spatial randomization.

Improved class-wise domain invariant feature learning.

Abstract

Currently, cross-scene hyperspectral image (HSI) classification has drawn increasing attention. It is necessary to train a model only on source domain (SD) and directly transferring the model to target domain (TD), when TD needs to be processed in real time and cannot be reused for training. Based on the idea of domain generalization, a Single-source Domain Expansion Network (SDEnet) is developed to ensure the reliability and effectiveness of domain extension. The method uses generative adversarial learning to train in SD and test in TD. A generator including semantic encoder and morph encoder is designed to generate the extended domain (ED) based on encoder-randomization-decoder architecture, where spatial and spectral randomization are specifically used to generate variable spatial and spectral information, and the morphological knowledge is implicitly applied as domain invariant information during domain expansion. Furthermore, the supervised contrastive learning is employed in the discriminator to learn class-wise domain invariant representation, which drives intra-class samples of SD and ED. Meanwhile, adversarial training is designed to optimize the generator to drive intra-class samples of SD and ED to be separated. Extensive experiments on two public HSI datasets and one additional multispectral image (MSI) dataset demonstrate the superiority of the proposed method when compared with state-of-the-art techniques.