Rich feature representations derived from CLIP-ViT have been widely utilized in AI-generated image detection. While most existing methods primarily leverage features from the final layer, we systematically analyze the contributions of layer-wise features to this task. Our study reveals that earlier layers provide more localized and generalizable features, often surpassing the performance of final-layer features in detection tasks. Moreover, we find that different layers capture distinct aspects of the data, each contributing uniquely to AI-generated image detection. Motivated by these findings, we introduce a novel adaptive method, termed MoLD, which dynamically integrates features from multiple ViT layers using a gating-based mechanism. Extensive experiments on both GAN- and diffusion-generated images demonstrate that MoLD significantly improves detection performance, enhances generalization across diverse generative models, and exhibits robustness in real-world scenarios. Finally, we illustrate the scalability and versatility of our approach by successfully applying it to other pre-trained ViTs, such as DINOv2.

翻译：源自CLIP-ViT的丰富特征表示已广泛应用于AI生成图像检测领域。尽管现有方法主要利用最终层的特征，我们系统性地分析了各层级特征对此任务的贡献。研究发现，较早层级提供更具局部性和泛化能力的特征，在检测任务中往往超越最终层特征的性能。此外，我们发现不同层级捕获数据的不同方面，各自对AI生成图像检测做出独特贡献。基于这些发现，我们提出一种新颖的自适应方法MoLD，该方法通过基于门控的机制动态整合来自多个ViT层级的特征。在GAN生成和扩散生成图像上的大量实验表明，MoLD显著提升了检测性能，增强了对不同生成模型的泛化能力，并在实际场景中展现出鲁棒性。最后，我们通过将该方法成功应用于其他预训练ViT（如DINOv2），展示了其可扩展性和多功能性。