arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.14799cs.CVcs.CRcs.SI

视觉Mamba能否提升AI生成图像检测？一项深入研究

Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation

Laboratory of IEMN, CNRS, Centrale Lille, UMR 8520, Univ. Polytechnique Hauts-de-France（伊姆纳实验室，国家科学研究中心，里尔中央理工大学，UMR 8520，法国高等技术大学）；Khalifa University（卡利法大学）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi（索邦人工智能中心，索邦大学阿布扎克分校）

Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Xianxun Zhu, Abdenour Hadid

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究系统评估了Vision Mamba模型在AI生成图像检测中的性能，与CNN、ViT和VLM检测器进行对比，分析了准确性、效率和泛化能力。

摘要：

近年来，计算机视觉取得了显著进展，这得益于卷积神经网络（CNN）、生成对抗网络（GAN）、扩散架构、视觉Transformer（ViT）以及最近的视觉-语言模型（VLM）等创新架构的发展。这一进展无疑有助于创造越来越逼真和多样化的视觉内容。然而，图像生成的这些进步也引发了对错误信息、身份盗窃以及隐私和安全威胁等潜在滥用的担忧。与此同时，基于Mamba的架构已成为这一快速发展的领域中一系列图像分析任务（包括分类、分割、医学成像、目标检测和图像恢复）的多功能工具。然而，与已有技术相比，它们在识别AI生成图像方面的潜力仍相对未被探索。本研究提供了用于AI生成图像检测的Vision Mamba模型的系统评估和比较分析。我们在多样化的数据集和合成图像源上，将多个Vision Mamba变体与代表性的CNN、ViT和基于VLM的检测器进行基准测试，重点关注准确性、效率以及跨不同图像类型和生成模型的泛化能力等关键指标。通过这一全面分析，我们旨在阐明Vision Mamba相对于已有方法在检测AI生成图像方面的适用性、准确性和效率上的优势与局限性。总体而言，我们的研究结果突显了Vision Mamba作为区分真实与AI生成视觉内容的系统组件的潜力和当前局限性。这项研究对于在区分真实与AI生成内容成为重大挑战的时代提升检测能力至关重要。

英文摘要：

In recent years, computer vision has witnessed remarkable progress, fueled by the development of innovative architectures such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), diffusion-based architectures, Vision Transformers (ViTs), and, more recently, Vision-Language Models (VLMs). This progress has undeniably contributed to creating increasingly realistic and diverse visual content. However, such advancements in image generation also raise concerns about potential misuse in areas such as misinformation, identity theft, and threats to privacy and security. In parallel, Mamba-based architectures have emerged as versatile tools for a range of image analysis tasks, including classification, segmentation, medical imaging, object detection, and image restoration, in this rapidly evolving field. However, their potential for identifying AI-generated images remains relatively unexplored compared to established techniques. This study provides a systematic evaluation and comparative analysis of Vision Mamba models for AI-generated image detection. We benchmark multiple Vision Mamba variants against representative CNNs, ViTs, and VLM-based detectors across diverse datasets and synthetic image sources, focusing on key metrics such as accuracy, efficiency, and generalizability across diverse image types and generative models. Through this comprehensive analysis, we aim to elucidate Vision Mamba's strengths and limitations relative to established methodologies in terms of applicability, accuracy, and efficiency in detecting AI-generated images. Overall, our findings highlight both the promise and current limitations of Vision Mamba as a component in systems designed to distinguish authentic from AI-generated visual content. This research is crucial for enhancing detection in an age where distinguishing between real and AI-generated content is a major challenge.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑