UniGenDet：面向协同进化图像生成与生成图像检测的统一生成-判别框架
UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
把生成器与检测器放进同一框架做协同进化，用检测器提供的真实性信号反向引导生成、用生成任务提升真实性判别的可解释性，为「生成-取证」联合建模提供了可复用的统一微调与信息交换机制。
原文依据 we design a symbiotic multimodal self-attention mechanism and a unified fine-tuning algorithm
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，图像生成与生成图像检测两个领域均取得了显著进展。尽管二者发展迅速，却基本各自独立，并演化出不同的架构范式：前者主要依赖生成网络，后者则偏向判别式框架。两个领域近期的一个共同趋势是利用对抗信息提升性能，这揭示出二者协同的潜力。然而，二者之间显著的架构差异带来了相当大的挑战。与以往方法不同，我们提出 UniGenDet：一个用于协同进化图像生成与生成图像检测的统一生成-判别框架。为弥合任务间的鸿沟，我们设计了共生多模态自注意力机制与统一微调算法。这种协同使生成任务能够提升真实性鉴别的可解释性，同时真实性准则又引导生成更高保真度的图像。此外，我们引入检测器引导的生成对齐机制，以促进无缝的信息交换。在多个数据集上的大量实验表明，我们的方法达到了最优性能。代码：https://github.com/Zhangyr2022/UniGenDet。
英文原文摘要 1325 字符
In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the former predominantly relies on generative networks, while the latter favors discriminative frameworks. A recent trend in both domains is the use of adversarial information to enhance performance, revealing potential for synergy. However, the significant architectural divergence between them presents considerable challenges. Departing from previous approaches, we propose **UniGenDet**: a **Uni**fied generative-discriminative framework for co-evolutionary image **Gen**eration and generated image **Det**ection. To bridge the task gap, we design a symbiotic multimodal self-attention mechanism and a unified fine-tuning algorithm. This synergy allows the generation task to improve the interpretability of authenticity identification, while authenticity criteria guide the creation of higher-fidelity images. Furthermore, we introduce a detector-informed generative alignment mechanism to facilitate seamless information exchange. Extensive experiments on multiple datasets demonstrate that our method achieves state-of-the-art performance. Code: https://github.com/Zhangyr2022/UniGenDet.