# DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2607.15128 · HTML: https://mlsanity.com/paper/2607.15128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 16 Jul 2026.

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

- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [Graph Convolutional Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2008.02457/) (2020)
- [HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification](https://mlsanity.com/paper/1902.06701/) (2019)
- [Three dimensional Deep Learning approach for remote sensing image classification](https://mlsanity.com/paper/1806.05824/) (2018)
- [MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2501.04944/) (2025)
- [Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification](https://mlsanity.com/paper/1905.06133/) (2019)
- [Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing](https://mlsanity.com/paper/2105.10194/) (2021)
- [Spectral-Spatial Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.18401/) (2024)
- [A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models](https://mlsanity.com/paper/2404.14955/) (2024)
- [GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2407.08255/) (2024)
- [Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification](https://mlsanity.com/paper/2106.13952/) (2021)
- [Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2204.05823/) (2022)
- [Spatio-Spectral Structure Tensor Total Variation for Hyperspectral Image Denoising and Destriping](https://mlsanity.com/paper/2404.03313/) (2024)
- [Physics-Informed Spectral Modeling for Hyperspectral Imaging](https://mlsanity.com/paper/2508.21618/) (2025)

## Abstract (arXiv)

Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI classifiers usually construct graph topology from spatial proximity, superpixel connectivity, or learned feature affinity. However, the spectral physical prior carried by contiguous bands has limited influence on topology estimation and message propagation. This paper presents DAPGNet, a dynamic adaptive physics-guided graph diffusion network that injects a structure-constrained physical prior into relation-level graph learning. DAPGNet first encodes contiguous spectral responses into node-wise multiscale physical-prior representations. A two-stage graph constructor then combines spectral-spatial affinity, physical-prior consistency, and spatial distance to form a physical-prior-aware sparse topology. During graph diffusion, learned edge weights are transformed into additive attention biases, while a physical gate performs node-wise and feature-wise interpolation between graph-aggregated features and projected physical-prior features. Cross-scale fusion integrates node states from different diffusion depths, and the network is optimized with main classification, auxiliary supervision, and second-order spectral smoothness regularization. Experiments on Indian Pines, WHU-Hi-LongKou, Houston2013, and Houston2018 show that DAPGNet achieves the best OA, AA, and Kappa among representative CNN-, Transformer-, Mamba-, and graph-based baselines. It improves AA over the strongest competing method by 3.64 to 7.31 percentage points across the four datasets. Ablation and sensitivity analyses further support the complementary effects of physical-prior extraction, prior-aware topology construction, physics-gated propagation, and spectral smoothness regularization.