Transformers Meet Hyperspectral Imaging: A Comprehensive Study of Models, Challenges and Open Problems
This survey guides researchers in adapting Transformers for hyperspectral imaging applications, addressing domain-specific bottlenecks in a rapidly emerging field.
The paper presents the first comprehensive survey of Transformer-based models for hyperspectral imaging classification, reviewing over 300 papers to analyze design choices and challenges like scarce labeled data and computational overhead.
Transformers have become the architecture of choice for learning long-range dependencies, yet their adoption in hyperspectral imaging (HSI) is still emerging. We reviewed more than 300 papers published up to 2025 and present the first end-to-end survey dedicated to Transformer-based HSI classification. The study categorizes every stage of a typical pipeline-pre-processing, patch or pixel tokenization, positional encoding, spatial-spectral feature extraction, multi-head self-attention variants, skip connections, and loss design-and contrasts alternative design choices with the unique spatial-spectral properties of HSI. We map the field's progress against persistent obstacles: scarce labeled data, extreme spectral dimensionality, computational overhead, and limited model explainability. Finally, we outline a research agenda prioritizing valuable public data sets, lightweight on-edge models, illumination and sensor shifts robustness, and intrinsically interpretable attention mechanisms. Our goal is to guide researchers in selecting, combining, or extending Transformer components that are truly fit for purpose for next-generation HSI applications.