提出抗干扰的红外可见光图像融合网络，提升对抗攻击下的融合质量。
$\textrm{A}^{\textrm{2}}$RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion
- 基于对抗训练与防御优化模块，构建鲁棒融合框架
- 在对抗扰动下仍保持高质量融合结果，性能优于以往方法
- 适合需要高可靠性图像融合的应用场景
红外与可见光图像融合（IVIF）通过整合多模态信息提升视觉表现，现有方法多关注无干扰数据下的融合效果，忽视了恶意干扰对融合性能的影响。本文提出一种新型抗对抗攻击网络A²RNet，设计基于IVIF内在特性的对抗攻击与训练范式，结合带有变压器结构的防御精炼模块（DRM）的U-Net架构，实现从粗到精的鲁棒融合。实验表明，该方法能有效缓解对抗扰动的负面影响，在多种攻击下仍保持高保真融合结果，下游任务性能亦得以维持。代码已开源：https://github.com/lok-18/A2RNet。
原文摘要 · Abstract (English)
Infrared and visible image fusion (IVIF) is a crucial technique for enhancing visual performance by integrating unique information from different modalities into one fused image. Exiting methods pay more attention to conducting fusion with undisturbed data, while overlooking the impact of deliberate interference on the effectiveness of fusion results. To investigate the robustness of fusion models, in this paper, we propose a novel adversarial attack resilient network, called $\textrm{A}^{\textrm{2}}$RNet. Specifically, we develop an adversarial paradigm with an anti-attack loss function to implement adversarial attacks and training. It is constructed based on the intrinsic nature of IVIF and provide a robust foundation for future research advancements. We adopt a Unet as the pipeline with a transformer-based defensive refinement module (DRM) under this paradigm, which guarantees fused image quality in a robust coarse-to-fine manner. Compared to previous works, our method mitigates the adverse effects of adversarial perturbations, consistently maintaining high-fidelity fusion results. Furthermore, the performance of downstream tasks can also be well maintained under adversarial attacks. Code is available at https://github.com/lok-18/A2RNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。