# DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging

arXiv: https://arxiv.org/abs/2503.00905 · HTML: https://mlsanity.com/paper/2503.00905/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 59 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 27 of 27)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [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)
- [Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation](https://mlsanity.com/paper/2308.02097/) (2023)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images](https://mlsanity.com/paper/2304.05172/) (2023)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration](https://mlsanity.com/paper/1903.08817/) (2019)
- [CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion](https://mlsanity.com/paper/2211.10960/) (2022)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion](https://mlsanity.com/paper/2305.15862/) (2023)
- [Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption](https://mlsanity.com/paper/2501.10761/) (2025)
- [An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection](https://mlsanity.com/paper/2305.09999/) (2023)
- [Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution](https://mlsanity.com/paper/2303.05156/) (2023)
- [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)
- [KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution](https://mlsanity.com/paper/2209.10305/) (2022)
- [Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond](https://mlsanity.com/paper/1711.06787/) (2017)
- [Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy](https://mlsanity.com/paper/2405.09927/) (2024)
- [On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems](https://mlsanity.com/paper/1808.05331/) (2018)
- [Infrared Image Super-Resolution: Systematic Review, and Future Trends](https://mlsanity.com/paper/2212.12322/) (2022)
- [Searching a Compact Architecture for Robust Multi-Exposure Image Fusion](https://mlsanity.com/paper/2305.12236/) (2023)
- [AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation](https://mlsanity.com/paper/2405.11467/) (2024)
- [DALE : Dark Region-Aware Low-light Image Enhancement](https://mlsanity.com/paper/2008.12493/) (2020)
- [Hierarchical Optimization-Derived Learning](https://mlsanity.com/paper/2302.05587/) (2023)

## Built on by (most cited first, 7 of 7)

- [Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion](https://mlsanity.com/paper/2503.07235/) (2025)
- [Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark](https://mlsanity.com/paper/2510.09343/) (2025)
- [TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization](https://mlsanity.com/paper/2508.03727/) (2025)
- [Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement](https://mlsanity.com/paper/2604.22886/) (2026)
- [Expandable, Compressible, Mineable: Open-World Thermal Image Restoration](https://mlsanity.com/paper/2605.16967/) (2026)
- [Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation](https://mlsanity.com/paper/2605.14346/) (2026)
- [TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index](https://mlsanity.com/paper/2606.19813/) (2026)

## Abstract (arXiv)

Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.