# SSFT: A Lightweight Spectral-Spatial Fusion Transformer for Generic Hyperspectral Classification

arXiv: https://arxiv.org/abs/2604.15828 · HTML: https://mlsanity.com/paper/2604.15828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification](https://mlsanity.com/paper/1902.06701/) (2019)
- [Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects](https://mlsanity.com/paper/2101.06116/) (2021)
- [SpectralEarth: Training Hyperspectral Foundation Models at Scale](https://mlsanity.com/paper/2408.08447/) (2024)
- [A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples](https://mlsanity.com/paper/2112.01800/) (2021)
- [Hyperspectral Image Classification with Attention Aided CNNs](https://mlsanity.com/paper/2005.11977/) (2020)
- [Measuring the Ripeness of Fruit with Hyperspectral Imaging and Deep Learning](https://mlsanity.com/paper/2104.09808/) (2021)
- [Wavelength-aware 2D Convolutions for Hyperspectral Imaging](https://mlsanity.com/paper/2209.03136/) (2022)
- [GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets](https://mlsanity.com/paper/2408.14131/) (2024)
- [GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction](https://mlsanity.com/paper/2507.06806/) (2025)
- [Hyperspectral Data Augmentation](https://mlsanity.com/paper/1903.05580/) (2019)
- [Hyperspectral Benchmark: Bridging the Gap between HSI Applications through Comprehensive Dataset and Pretraining](https://mlsanity.com/paper/2309.11122/) (2023)

## Abstract (arXiv)

Hyperspectral imaging enables fine-grained recognition of materials by capturing rich spectral signatures, but learning robust classifiers is challenging due to high dimensionality, spectral redundancy, limited labeled data, and strong domain shifts. Beyond earth observation, labeled HSI data is often scarce and imbalanced, motivating compact models for generic hyperspectral classification across diverse acquisition regimes. We propose the lightweight Spectral-Spatial Fusion Transformer (SSFT), which factorizes representation learning into spectral and spatial pathways and integrates them via cross-attention to capture complementary wavelength-dependent and structural information. We evaluate our SSFT on the challenging HSI-Benchmark, a heterogeneous multi-dataset benchmark covering earth observation, fruit condition assessment, and fine-grained material recognition. SSFT achieves state-of-the-art overall performance, ranking first while using less than 2% of the parameters of the previous leading method. We further evaluate transfer to the substantially larger SpectralEarth benchmark under the official protocol, where SSFT remains competitive despite its compact size. Ablation studies show that both spectral and spatial pathways are crucial, with spatial modeling contributing most, and that SSFT remains robust without data augmentation.