Prototype-Guided Class-Balanced Active Domain Adaptation for Hyperspectral Image Classification

Haiyang Luo, Shengwei Zhong, Chen Gong

Abstract: The high cost of data annotation has become a major factor restricting the hyperspectral image (HSI) classification task. To address this issue, domain adaptation (DA) techniques have been developed to adapt models trained on abundantly labeled HSIs to those with scarce labels. As a novel DA paradigm, active DA (ADA) seeks to selectively annotate informative examples using active learning (AL) techniques under domain shift scenarios, ultimately enhancing model adaptation performance. However, current ADA methods require annotating a relatively large number of target examples, which is impractical for HSIs. In addition, the target HSIs suffer from class imbalance, which limits the adaptation performance. To address the above issues, this article proposes a prototype-guided class-balanced ADA (PCADA) method for HSI classification. PCADA alternately aligns the distributions between domains through prototype guidance and selects the most valuable target examples for annotation. Specifically, a prototype-guided domain alignment (PGDA) module is introduced, which generates target prototypes based on highly confident pseudolabels and aligns the distributions of two domains. The inconsistency-aware example selection (IES) module identifies target-specific examples and selects the most valuable ones for annotation. Furthermore, we propose a class-balanced self-training (CBST) module that generates pseudolabels with balanced class distribution to solve the class imbalance issue in the target domain. The experimental results conducted on multiple benchmark HSI datasets demonstrate the superior performance of our proposed method. The code will be available at: https://github.com/Leap-luohaiyang/PCADA-2025

External IDs:dblp:journals/tgrs/LuoZG25