Cross-domain few-shot learning for hyperspectral image classification based on mixup foundation model

Although cross-domain few-shot learning (CDFSL) for hyperspectral image (HSI) classification has attracted significant research interest, existing works often rely on an unrealistic data augmentation procedure in the form of external noise to enlarge the sample size, thus greatly simplifying the issue of data scarcity. They involve a large number of parameters for model updates, being prone to the overfitting problem. To the best of our knowledge, only one work has explored the strength of the foundation model, yet it still relies on a conventional foundation model for RGB images. This paper proposes the MIxup FOundation MOdel (MIFOMO) for CDFSL of HSI classifications. MIFOMO is built upon the concept of a remote sensing (RS) foundation model, pre-trained across a large scale of RS problems, thus featuring generalizable features. The notion of coalescent projection (CP) is introduced to quickly adapt the foundation model to downstream tasks while freezing the backbone network. The concept of mixup domain adaptation (MDM) is proposed to address the extreme domain discrepancy problem. Last but not least, the label propagation concept is implemented to cope with noisy pseudo-label problems. Our rigorous experiments demonstrate the advantage of MIFOMO, where it beats prior art by up to a 14% margin. The source code of MIFOMO is open-sourced in https://github.com/Naeem-Paeedeh/MIFOMO for reproducibility and further study.