Few-Shot Multispectral-Hyperspectral Image Collaborative Classification With Feature Distribution Enhancement and Subdomain Alignment

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-17
• Main Authors: Guo, Bin, Liu, Tianzhu, Zhang, Xiangrong, Gu, Yanfeng
• Format: Article
• Language: English
• Subjects: Alignment; Bias; Classification; Collaboration; Convolution; Distribution; Hyperspectral imaging; Image classification; Image enhancement; Modules; Spectral resolution
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3351846

With the development of observation technology, multispectral (MS) images of large scenes are easy to obtain, but the low spectral resolution limits their classification ability. Moreover, the collection of training samples is difficult and time-consuming, and limited labeled samples are a challenge for the precise classification of large-scene MS images. This article attempts to use hyperspectral (HS) images with limited labels to help classify MS images of large scenes, so as to achieve better classification results. To solve this problem, a few-shot MS-HS image collaborative classification method combining feature distribution enhancement (FDE) and subdomain alignment is proposed. Specifically, a residual 3-D convolution network embedded with a 3-D FDE module is designed to improve the diversity of the feature distribution extracted by the network and increase the generalization ability of the model under the few-shot condition. Furthermore, the local domain alignment between the source and target domains is achieved by subdomain alignment, which better aligns the categories in the source domain and the target domain, and achieves the distribution alignment of the subdomains. In addition, the feature bias adjustment (FBA) module is introduced in the test phase to correct the bias of the MS image feature representation, and to alleviate the cross-domain problem to some extent. The few-shot learning (FSL) is applied in the source and target domains to learn better feature mapping. The results of comparative experiments on three datasets show that the proposed method is superior to the most advanced method in the case of limited labeled samples.