# Cross-Domain Transfer with Self-Supervised Spectral-Spatial Modeling for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2601.18088 · HTML: https://mlsanity.com/paper/2601.18088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Contrastive Domain Adaptation](https://mlsanity.com/paper/2103.15566/) (2021)
- [Test-time adaptation for geospatial point cloud semantic segmentation with distinct domain shifts](https://mlsanity.com/paper/2407.06043/) (2024)
- [Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation](https://mlsanity.com/paper/2202.03968/) (2022)
- [Domain Adaptable Self-supervised Representation Learning on Remote Sensing Satellite Imagery](https://mlsanity.com/paper/2304.09874/) (2023)

## Abstract (arXiv)

Self-supervised learning has demonstrated considerable potential in hyperspectral representation, yet its application in cross-domain transfer scenarios remains under-explored. Existing methods, however, still rely on source domain annotations and are susceptible to distribution shifts, leading to degraded generalization performance in the target domain. To address this, this paper proposes a self-supervised cross-domain transfer framework that learns transferable spectral-spatial joint representations without source labels and achieves efficient adaptation under few samples in the target domain. During the self-supervised pre-training phase, a Spatial-Spectral Transformer (S2Former) module is designed. It adopts a dual-branch spatial-spectral transformer and introduces a bidirectional cross-attention mechanism to achieve spectral-spatial collaborative modeling: the spatial branch enhances structural awareness through random masking, while the spectral branch captures fine-grained differences. Both branches mutually guide each other to improve semantic consistency. We further propose a Frequency Domain Constraint (FDC) to maintain frequency-domain consistency through real Fast Fourier Transform (rFFT) and high-frequency magnitude loss, thereby enhancing the model's capability to discern fine details and boundaries. During the fine-tuning phase, we introduce a Diffusion-Aligned Fine-tuning (DAFT) distillation mechanism. This aligns semantic evolution trajectories through a teacher-student structure, enabling robust transfer learning under low-label conditions. Experimental results demonstrate stable classification performance and strong cross-domain adaptability across four hyperspectral datasets, validating the method's effectiveness under resource-constrained conditions.