A Novel Conditional Alignment and Pseudolabel Generation Method for Cross-Scene Hyperspectral Image Classification

A key bottleneck in cross-scene hyperspectral image (HSI) classification comes from domain shift, which poses a significant challenge for applying network models to some new, unlabeled scenes. Unsupervised domain adaptation, which aims to align the distributions of the source and target domains, has emerged as a powerful technique to address this challenge. In this paper, we propose a novel method named conditional alignment and pseudo label generation (CAPLG), which mainly consists of three contributions. Firstly, to address the issue of misaligned conditional distributions between domains, a conditional maximum direction discrepancy (CMDD) strategy is proposed, which explicitly models the directional discrepancy of inter-domain category features. By minimizing CMDD, the alignment of domain conditional distributions can be achieved. Secondly, spectral pseudo label (SpePL) and spatial pseudo label (SpaPL) are designed to fully learn the spectral and spatial information of the target domain. The SpePLs can also provide high-quality label guidance for CMDD in the early stages of training. Thirdly, to address the alignment problem caused by spatial resolution mismatch across domains, a pixel patch unified network (PPUN) was constructed, which enables sufficient transfer of spatial information under varying resolutions and ensures the more efficient generation of the SpaPLs. A comparative evaluation of the proposed method with some state-of-the-art methods was conducted on three cross-scene HSI datasets. The experimental results show that our proposed method achieves excellent performance on all three datasets.