# Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification

arXiv: https://arxiv.org/abs/2509.23310 · HTML: https://mlsanity.com/paper/2509.23310/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 19 of its 64 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [MambaOut: Do We Really Need Mamba for Vision?](https://mlsanity.com/paper/2405.07992/) (2024)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review](https://mlsanity.com/paper/2205.01380/) (2022)
- [Multimodal Fusion Transformer for Remote Sensing Image Classification](https://mlsanity.com/paper/2203.16952/) (2022)
- [Diffusion Models Beat GANs on Image Classification](https://mlsanity.com/paper/2307.08702/) (2023)
- [On-the-fly Modulation for Balanced Multimodal Learning](https://mlsanity.com/paper/2410.11582/) (2024)
- [SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models](https://mlsanity.com/paper/2304.05961/) (2023)
- [Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives](https://mlsanity.com/paper/2404.08926/) (2024)
- [SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification](https://mlsanity.com/paper/2311.04442/) (2023)
- [A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models](https://mlsanity.com/paper/2404.14955/) (2024)
- [Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification](https://mlsanity.com/paper/2306.08964/) (2023)
- [MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image Classification](https://mlsanity.com/paper/2408.14255/) (2024)
- [Siamese Meets Diffusion Network: SMDNet for Enhanced Change Detection in High-Resolution RS Imagery](https://mlsanity.com/paper/2401.09325/) (2024)
- [DiffUCD:Unsupervised Hyperspectral Image Change Detection with Semantic Correlation Diffusion Model](https://mlsanity.com/paper/2305.12410/) (2023)
- [MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching](https://mlsanity.com/paper/2501.11299/) (2025)

## Built on by (most cited first, 1 of 1)

- [TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation](https://mlsanity.com/paper/2603.19039/) (2026)

## Abstract (arXiv)

Deep learning-based techniques for the analysis of multimodal remote sensing data have become popular due to their ability to effectively integrate complementary spatial, spectral, and structural information from different sensors. Recently, denoising diffusion probabilistic models (DDPMs) have attracted attention in the remote sensing community due to their powerful ability to capture robust and complex spatial-spectral distributions. However, pre-training multimodal DDPMs may result in modality imbalance, and effectively leveraging diffusion features to guide complementary diversity feature extraction remains an open question. To address these issues, this paper proposes a balanced diffusion-guided fusion (BDGF) framework that leverages multimodal diffusion features to guide a multi-branch network for land-cover classification. Specifically, we propose an adaptive modality masking strategy to encourage the DDPMs to obtain a modality-balanced rather than spectral image-dominated data distribution. Subsequently, these diffusion features hierarchically guide feature extraction among CNN, Mamba, and transformer networks by integrating feature fusion, group channel attention, and cross-attention mechanisms. Finally, a mutual learning strategy is developed to enhance inter-branch collaboration by aligning the probability entropy and feature similarity of individual subnetworks. Extensive experiments on four multimodal remote sensing datasets demonstrate that the proposed method achieves superior classification performance. The code is available at https://github.com/HaoLiu-XDU/BDGF.