Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification
This addresses the problem of real-time classification in target domains without training data for remote sensing applications, though it appears incremental as it builds on domain generalization and adversarial learning techniques.
The paper tackled cross-scene hyperspectral image classification by developing a Single-source Domain Expansion Network (SDEnet) that uses generative adversarial learning and supervised contrastive learning to train on a source domain and test on a target domain, achieving superior performance compared to state-of-the-art methods on two HSI datasets and one MSI dataset.
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.