# Task-driven Image Fusion with Learnable Fusion Loss

arXiv: https://arxiv.org/abs/2412.03240 · HTML: https://mlsanity.com/paper/2412.03240/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 88 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 30 of 37)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [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)
- [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)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion](https://mlsanity.com/paper/2303.06840/) (2023)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation](https://mlsanity.com/paper/2308.02097/) (2023)
- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [Equivariant Multi-Modality Image Fusion](https://mlsanity.com/paper/2305.11443/) (2023)
- [Evolved Policy Gradients](https://mlsanity.com/paper/1802.04821/) (2018)
- [Single Image Deraining: A Comprehensive Benchmark Analysis](https://mlsanity.com/paper/1903.08558/) (2019)
- [Dynamic Instance Normalization for Arbitrary Style Transfer](https://mlsanity.com/paper/1911.06953/) (2019)
- [Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration](https://mlsanity.com/paper/2205.11876/) (2022)
- [Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion](https://mlsanity.com/paper/1910.04066/) (2019)
- [DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2003.09210/) (2020)
- [CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion](https://mlsanity.com/paper/2211.10960/) (2022)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Task-Driven Super Resolution: Object Detection in Low-resolution Images](https://mlsanity.com/paper/1803.11316/) (2018)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion](https://mlsanity.com/paper/2305.15862/) (2023)
- [USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s](https://mlsanity.com/paper/2409.08481/) (2024)
- [Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond](https://mlsanity.com/paper/2305.06720/) (2023)
- [PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation](https://mlsanity.com/paper/2308.03979/) (2023)

## Built on by (most cited first, 25 of 25)

- [Neural Video Compression with Context Modulation](https://mlsanity.com/paper/2505.14541/) (2025)
- [A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking](https://mlsanity.com/paper/2505.19858/) (2025)
- [Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion](https://mlsanity.com/paper/2503.07235/) (2025)
- [DEPFusion: Dual-Domain Enhancement and Priority-Guided Mamba Fusion for UAV Multispectral Object Detection](https://mlsanity.com/paper/2509.07327/) (2025)
- [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)
- [MambaVF: State Space Model for Efficient Video Fusion](https://mlsanity.com/paper/2602.06017/) (2026)
- [PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications](https://mlsanity.com/paper/2603.23071/) (2026)
- [Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion](https://mlsanity.com/paper/2604.08924/) (2026)
- [GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting](https://mlsanity.com/paper/2604.18047/) (2026)
- [Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images](https://mlsanity.com/paper/2605.13049/) (2026)
- [From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion](https://mlsanity.com/paper/2606.12303/) (2026)
- [Localization-Infused Vision-Language Semantic Fusion for Text-Guided Medical Image Segmentation](https://mlsanity.com/paper/2607.16327/) (2026)
- [One Latent Space to Rule All Degradations: Unifying Restoration Knowledge for Image Fusion](https://mlsanity.com/paper/2503.07033/) (2025)
- [EPOFusion: Exposure aware Progressive Optimization Method for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2603.16130/) (2026)
- [MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction](https://mlsanity.com/paper/2604.01958/) (2026)
- [EAPFusion: Intrinsic Evolving Auxiliary Prior Guidance for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2605.01916/) (2026)
- [FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion](https://mlsanity.com/paper/2606.07985/) (2026)
- [Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction](https://mlsanity.com/paper/2606.26812/) (2026)
- [Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmark](https://mlsanity.com/paper/2607.08191/) (2026)
- [UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion](https://mlsanity.com/paper/2608.21786/) (2026)
- [SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion](https://mlsanity.com/paper/2609.30703/) (2026)
- [Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion](https://mlsanity.com/paper/2609.38968/) (2026)
- [When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion](https://mlsanity.com/paper/2609.39004/) (2026)
- [AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image Fusion](https://mlsanity.com/paper/2610.12897/) (2026)

## Abstract (arXiv)

Multi-modal image fusion aggregates information from multiple sensor sources, achieving superior visual quality and perceptual features compared to single-source images, often improving downstream tasks. However, current fusion methods for downstream tasks still use predefined fusion objectives that potentially mismatch the downstream tasks, limiting adaptive guidance and reducing model flexibility. To address this, we propose Task-driven Image Fusion (TDFusion), a fusion framework incorporating a learnable fusion loss guided by task loss. Specifically, our fusion loss includes learnable parameters modeled by a neural network called the loss generation module. This module is supervised by the downstream task loss in a meta-learning manner. The learning objective is to minimize the task loss of fused images after optimizing the fusion module with the fusion loss. Iterative updates between the fusion module and the loss module ensure that the fusion network evolves toward minimizing task loss, guiding the fusion process toward the task objectives. TDFusion's training relies entirely on the downstream task loss, making it adaptable to any specific task. It can be applied to any architecture of fusion and task networks. Experiments demonstrate TDFusion's performance through fusion experiments conducted on four different datasets, in addition to evaluations on semantic segmentation and object detection tasks.