# MDFL: Multi-domain Diffusion-driven Feature Learning

arXiv: https://arxiv.org/abs/2311.09520 · HTML: https://mlsanity.com/paper/2311.09520/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022)
- [HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging](https://mlsanity.com/paper/2203.02149/) (2022)
- [DINE: Domain Adaptation from Single and Multiple Black-box Predictors](https://mlsanity.com/paper/2104.01539/) (2021)
- [Hierarchy Parsing for Image Captioning](https://mlsanity.com/paper/1909.03918/) (2019)
- [Phase-only Image Based Kernel Estimation for Single-image Blind Deblurring](https://mlsanity.com/paper/1811.10185/) (2018)
- [Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification](https://mlsanity.com/paper/2306.08964/) (2023)

## Built on by (most cited first, 8 of 8)

- [Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives](https://mlsanity.com/paper/2404.08926/) (2024)
- [Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?](https://mlsanity.com/paper/2503.07890/) (2025)
- [Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification](https://mlsanity.com/paper/2401.03179/) (2024)
- [Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning](https://mlsanity.com/paper/2312.16246/) (2023)
- [M3amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification](https://mlsanity.com/paper/2503.06446/) (2025)
- [Diffusion Models for Hyperspectral Image Analysis: A Comprehensive Review](https://mlsanity.com/paper/2505.11158/) (2025)
- [FusionSAM: Visual Multi-Modal Learning with Segment Anything](https://mlsanity.com/paper/2408.13980/) (2024)
- [COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data](https://mlsanity.com/paper/2603.03239/) (2026)

## Abstract (arXiv)

High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information reveals the potential spectral representations across different bands. Currently, the understanding of high-dimensional images remains limited to a single-domain perspective with performance degradation. Motivated by the masking texture effect observed in the human visual system, we present a multi-domain diffusion-driven feature learning network (MDFL) , a scheme to redefine the effective information domain that the model really focuses on. This method employs diffusion-based posterior sampling to explicitly consider joint information interactions between the high-dimensional manifold structures in the spectral, spatial, and frequency domains, thereby eliminating the influence of masking texture effects in visual models. Additionally, we introduce a feature reuse mechanism to gather deep and raw features of high-dimensional data. We demonstrate that MDFL significantly improves the feature extraction performance of high-dimensional data, thereby providing a powerful aid for revealing the intrinsic patterns and structures of such data. The experimental results on three multi-modal remote sensing datasets show that MDFL reaches an average overall accuracy of 98.25%, outperforming various state-of-the-art baseline schemes. The code will be released, contributing to the computer vision community.