Transformer-Driven Active Transfer Learning for Cross-Hyperspectral Image Classification

TL;DR

This paper introduces a novel Transformer-based Active Transfer Learning framework for hyperspectral image classification, effectively reducing labeling costs and improving accuracy through strategic sample selection and dynamic model adaptation.

Contribution

It proposes a multistage transfer learning approach with an uncertainty-diversity-driven active learning mechanism and a dynamic layer freezing strategy for hyperspectral image classification.

Findings

Achieves superior classification performance on benchmark datasets.

Reduces labeling costs significantly compared to traditional methods.

Enhances transferability and computational efficiency through dynamic layer freezing.

Abstract

Hyperspectral image (HSI) classification presents inherent challenges due to high spectral dimensionality, significant domain shifts, and limited availability of labeled data. To address these issues, we propose a novel Active Transfer Learning (ATL) framework built upon a Spatial-Spectral Transformer (SST) backbone. The framework integrates multistage transfer learning with an uncertainty-diversity-driven active learning mechanism that strategically selects highly informative and diverse samples for annotation, thereby significantly reducing labeling costs and mitigating sample redundancy. A dynamic layer freezing strategy is introduced to enhance transferability and computational efficiency, enabling selective adaptation of model layers based on domain shift characteristics. Furthermore, we incorporate a self-calibrated attention mechanism that dynamically refines spatial and spectral weights during adaptation, guided by uncertainty-aware feedback. A diversity-promoting sampling strategy ensures broad spectral coverage among selected samples, preventing overfitting to specific classes. Extensive experiments on benchmark cross-domain HSI datasets demonstrate that the proposed SST-ATL framework achieves superior classification performance compared to conventional approaches. The source code is publicly available at https://github.com/mahmad000/ATL-SST.