通过全局与局部注意力融合，提升高分辨率生成图像检测精度。
Attention to Detail: Global-Local Attention for High-Resolution AI-Generated Image Detection
- 用分层采样选取原分辨率局部区域，结合全局图像视图
- 在多个数据集上显著优于传统下采样方法，准确率提升6.2%以上
- 适用于任意尺寸图像，适合需要细节识别的检测场景
生成式AI的快速发展使得人工智能生成图像愈发逼真且分辨率更高。现有检测架构通常在输入模型前对图像进行下采样，可能丢失细微特征。本文提出GLASS（基于分层采样的全局-局部注意力），将全局缩放视图与多个随机采样的局部补丁相结合。这些补丁是通过空间分层采样高效选取的原始分辨率区域，并利用注意力机制进行加权聚合。GLASS可嵌入各类视觉模型中，同时利用图像的全局与局部信息，支持任意尺寸输入。实验使用Vision Transformer、ResNet和ConvNeXt作为骨干网络，在多个数据集上验证表明，相比标准迁移学习，GLASS在可接受的计算开销下实现了更高的预测性能，准确率提升超过6.2%。
原文摘要 · Abstract (English)
The rapid development of generative AI has made AI-generated images increasingly realistic and high-resolution. Most AI-generated image detection architectures typically downsample images before inputting them into models, risking the loss of fine-grained details. This paper presents GLASS (Global-Local Attention with Stratified Sampling), an architecture that combines a globally resized view with multiple randomly sampled local crops. These crops are original-resolution regions efficiently selected through spatially stratified sampling and aggregated using attention-based scoring. GLASS can be integrated into vision models to leverage both global and local information in images of any size. Vision Transformer, ResNet, and ConvNeXt models are used as backbones, and experiments show that GLASS outperforms standard transfer learning by achieving higher predictive performance within feasible computational constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。