频域AI生成图像检测：探索解码器与通道注意力进行特征细化
Frequency-Domain AI-Generated Image Detection: Exploring Decoder and Channel Attention for Feature Refinement
浏览论文内容
中文总结 AI 辅助
本研究提出使用FFT与EfficientNet-B0结合解码器（U-Net、Attention U-Net）和通道注意力（ECA）进行频域AI生成图像检测，其中Attention U-Net达到最佳准确率85.51%。
中文摘要 AI 辅助
随着人工智能的快速发展，近年来AI生成图像的数量显著增加。然而，图像生成模型种类的日益增多使得检测变得更加困难。在本工作中，我们使用快速傅里叶变换（FFT）表示与EfficientNet-B0进行AI生成图像检测。EfficientNet-B0提供了轻量级架构，可用于资源受限的应用。大多数频域检测器使用标准编码器从FFT频谱中提取特征，并直接将其传递给分类器。我们探索了一种不同的方法，研究ECA、U-Net和Attention U-Net作为这种直接编码器到分类器方法的替代方案。ECA应用通道注意力，而U-Net和Attention U-Net使用基于解码器的架构来恢复和细化提取的频率特征中的空间信息。我们使用了MS COCOAI数据集的一个平衡子集，该子集包含来自五种不同模型的AI生成图像。每个实验进行了三次运行，并记录了平均值。实验结果表明，EfficientNet-B0获得了84.64%的准确率，比数据集论文中报告的ResNet-50基线高出4.50个百分点。EfficientNet-B0与U-Net结合提供了小幅改进，准确率达到84.85%，而ECA并未提高整体性能。EfficientNet-B0与Attention U-Net结合取得了最佳整体性能，准确率为85.51%，ROC-AUC为92.99%。与EfficientNet-B0基线相比，准确率提高了0.87个百分点，比数据集论文中报告的ResNet-50基线提高了5.37个百分点。
英文摘要
With the rapid progress of AI, the number of AI-generated images has increased significantly in recent years. However, the increasing variety of image generation models makes detection more difficult. In this work, we use Fast Fourier Transform (FFT) representation with EfficientNet-B0 for AI-generated image detection. EfficientNet-B0 provides a lightweight architecture that can be useful for resource-limited applications. Most frequency-domain detectors use a standard encoder to extract features from the FFT spectrum and directly pass them to a classifier. We explored a different approach by investigating ECA, U-Net, and Attention U-Net as alternatives to this direct encoder-to-classifier approach. ECA applies channel attention, while U-Net and Attention U-Net use decoder-based architectures to recover and refine spatial information in the extracted frequency features. We used a balanced subset of the MS COCOAI dataset that includes AI-generated images from five different models. Three runs were carried out for each experiment, and the average values were recorded. Experimental results indicate that EfficientNet-B0 obtained an accuracy of 84.64%, which is 4.50 percentage points higher than the ResNet-50 baseline reported in the dataset paper. EfficientNet-B0 with U-Net provided a small improvement, achieving an accuracy of 84.85%, while ECA did not increase the overall performance. EfficientNet-B0 with Attention U-Net achieved the best overall performance, with an accuracy of 85.51% and an ROC-AUC of 92.99%. This represents an improvement of 0.87 percentage points in accuracy compared to the EfficientNet-B0 baseline and 5.37 percentage points over the ResNet-50 baseline reported in the dataset paper.
