# MMDRFuse: Distilled Mini-Model with Dynamic Refresh for Multi-Modality Image Fusion

arXiv: https://arxiv.org/abs/2408.15641 · HTML: https://mlsanity.com/paper/2408.15641/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 28 Aug 2024.

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [Channel-wise Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/2011.13256/) (2020)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [Deep Gradient Projection Networks for Pan-sharpening](https://mlsanity.com/paper/2103.04584/) (2021)
- [TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion](https://mlsanity.com/paper/2312.14209/) (2023)
- [SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery](https://mlsanity.com/paper/2105.02400/) (2021)

## Built on by (most cited first, 10 of 10)

- [One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion](https://mlsanity.com/paper/2502.19854/) (2025)
- [Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion](https://mlsanity.com/paper/2511.06593/) (2025)
- [SMLNet: A SPD Manifold Learning Network for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2411.10679/) (2024)
- [FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration](https://mlsanity.com/paper/2603.07667/) (2026)
- [EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment](https://mlsanity.com/paper/2604.02896/) (2026)
- [Rethinking Normalization Strategies and Convolutional Kernels for Multimodal Image Fusion](https://mlsanity.com/paper/2411.10036/) (2024)
- [One Latent Space to Rule All Degradations: Unifying Restoration Knowledge for Image Fusion](https://mlsanity.com/paper/2503.07033/) (2025)
- [TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2506.16730/) (2025)
- [Interactive Spatial-Frequency Fusion Mamba for Multi-Modal Image Fusion](https://mlsanity.com/paper/2602.04405/) (2026)
- [Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion](https://mlsanity.com/paper/2603.21820/) (2026)

## Abstract (arXiv)

In recent years, Multi-Modality Image Fusion (MMIF) has been applied to many fields, which has attracted many scholars to endeavour to improve the fusion performance. However, the prevailing focus has predominantly been on the architecture design, rather than the training strategies. As a low-level vision task, image fusion is supposed to quickly deliver output images for observation and supporting downstream tasks. Thus, superfluous computational and storage overheads should be avoided. In this work, a lightweight Distilled Mini-Model with a Dynamic Refresh strategy (MMDRFuse) is proposed to achieve this objective. To pursue model parsimony, an extremely small convolutional network with a total of 113 trainable parameters (0.44 KB) is obtained by three carefully designed supervisions. First, digestible distillation is constructed by emphasising external spatial feature consistency, delivering soft supervision with balanced details and saliency for the target network. Second, we develop a comprehensive loss to balance the pixel, gradient, and perception clues from the source images. Third, an innovative dynamic refresh training strategy is used to collaborate history parameters and current supervision during training, together with an adaptive adjust function to optimise the fusion network. Extensive experiments on several public datasets demonstrate that our method exhibits promising advantages in terms of model efficiency and complexity, with superior performance in multiple image fusion tasks and downstream pedestrian detection application. The code of this work is publicly available at https://github.com/yanglinDeng/MMDRFuse.