Multi-level relation learning for cross-domain few-shot hyperspectral image classification

• DOI: 10.1007/s10489-024-05384-3
• Publication Date: 2024-03-26T08:04:21Z
• Authors: Chun Liu; Longwei Yang; Zheng Li; Wei Yang; Zhigang Han; Jianzhong Guo; Junyong Yu
• Keywords: FOS: Computer and information sciences; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0211 other engineering and technologies; 0202 electrical engineering, electronic engineering, information engineering

Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domains and then transferring the knowledge to the tasks which contain few labeled samples in target domains. Following the metric-based manner, many current methods first extract the features of the query and support samples, and then directly predict the classes of query samples according to their distance to the support samples or prototypes. The relations between samples have not been fully explored and utilized. Different from current works, this paper proposes to learn sample relations on different levels and take them into the model learning process, to improve the cross-domain few-shot hyperspectral image classification. Building on current method of "Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification" which adopts a domain discriminator to deal with domain-level distribution difference, the proposed method applies contrastive learning to learn the class-level sample relations to obtain more discriminable sample features. In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attention from query samples to support samples. Our experimental results have demonstrated the contribution of the multi-level relation learning mechanism for few-shot hyperspectral image classification when compared with the state of the art methods.