Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

TL;DR

This paper introduces a multi-level relation learning framework that enhances cross-domain few-shot hyperspectral image classification by utilizing class-level and set-level sample relations through contrastive learning and transformer-based attention.

Contribution

It proposes a novel multi-level relation learning approach that incorporates contrastive learning and cross-attention to improve feature discriminability in few-shot hyperspectral image classification.

Findings

Outperforms state-of-the-art methods in accuracy.

Effectively captures class and set-level relations.

Enhances feature discriminability for cross-domain tasks.

Abstract

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.