UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

arXiv:2604.21904v1 Announce Type: new Abstract: 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: href{https://github.com/Zhangyr2022/UniGenDet}{https://github.com/Zhangyr2022/UniGenDet}.

Related

• Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
• ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
• Rethinking Cross-Domain Evaluation for Face Forgery Detection with Semantic Fine-grained Alignment and Mixture-of-Experts
• Adversarial Concept Distillation for One-Step Diffusion Personalization

Source: arXiv cs.CV | 2026-04-24