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

2026-04-23

AI Summary

Image generation and generated image detection have long evolved in isolation, hindering their mutual performance improvement. This work proposes a unified generative-discriminative framework that enables cross-task feature alignment through a symbiotic multimodal self-attention mechanism. To foster bidirectional information exchange and joint optimization between generation and detection, the approach introduces a detector-guided generation alignment strategy alongside a unified fine-tuning algorithm. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method simultaneously achieves state-of-the-art performance in both image generation quality and forgery detection accuracy, thereby validating the efficacy of the unified architecture and its synergistic benefits.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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}.

Problem

• image generation
• generated image detection
• generative-discriminative framework
• architectural divergence
• co-evolutionary learning

Innovation

• Unified generative-discriminative framework
• Co-evolutionary learning
• Multimodal self-attention
• Detector-informed alignment
• Generated image detection