UniGenDet：一种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

摘要

近年来，图像生成与生成图像检测领域均取得显著进展。尽管二者发展迅速却相对独立，形成了截然不同的架构范式：前者主要依赖生成式网络，后者则倾向于判别式框架。当前这两个领域共同出现利用对抗信息提升性能的新趋势，展现出协同发展的潜力。然而，二者显著的架构差异带来了巨大挑战。不同于既往方法，我们提出UniGenDet：一个面向协同演进的图像生成与检测任务的统一生成-判别框架。为弥合任务鸿沟，我们设计了共生式多模态自注意力机制与统一微调算法。这种协同机制使生成任务能提升真实性判别的可解释性，而真实性标准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信息交换。在多数据集上的大量实验表明，本方法实现了最先进的性能。代码地址：https://github.com/Zhangyr2022/UniGenDet。

English

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 Unified generative-discriminative framework for co-evolutionary image Generation and generated image Detection. 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{https://github.com/Zhangyr2022/UniGenDet}.

UniGenDet：一种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

摘要

Support