揭示感知伪影：一个可解释AI生成图像检测的细粒度基准
Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection
AI总结：
本文提出X-AIGD基准，通过细粒度注释感知伪影，揭示现有AIGI检测器对伪影的依赖低，且需提升可解释性与泛化能力。
摘要：
当前AI生成图像（AIGI）检测方法主要依赖二元分类来区分真实图像与合成图像，往往缺乏可解释或有说服力的证据来支持其决策。这一局限性源于现有的AIGI检测基准，尽管包含了广泛的人工合成图像，但在覆盖伪影多样性方面仍受到限制，并且缺乏详细的、局部化的注释。为弥合这一差距，我们引入了一个细粒度的可解释AI生成图像检测基准，命名为X-AIGD，它提供了像素级别的、分类注释的感知伪影，涵盖低层次的失真、高层次的语义以及认知层面的反事实。这些全面的注释有助于细粒度可解释性评估，并深入理解模型的决策过程。我们的广泛研究使用X-AIGD提供了几个关键见解：（1）现有AIGI检测器对感知伪影的依赖极低，即使在最基本的失真级别也是如此。（2）尽管AIGI检测器可以训练以识别特定伪影，但它们仍然主要依赖于不可解释的特征。（3）显式地将模型注意力与伪影区域对齐可以提高检测器的可解释性和泛化能力。数据和代码可在：https://github.com/Coxy7/X-AIGD获取。
英文摘要：
Current AI-Generated Image (AIGI) detection approaches predominantly rely on binary classification to distinguish real from synthetic images, often lacking interpretable or convincing evidence to substantiate their decisions. This limitation stems from existing AIGI detection benchmarks, which, despite featuring a broad collection of synthetic images, remain restricted in their coverage of artifact diversity and lack detailed, localized annotations. To bridge this gap, we introduce a fine-grained benchmark towards eXplainable AI-Generated image Detection, named X-AIGD, which provides pixel-level, categorized annotations of perceptual artifacts, spanning low-level distortions, high-level semantics, and cognitive-level counterfactuals. These comprehensive annotations facilitate fine-grained interpretability evaluation and deeper insight into model decision-making processes. Our extensive investigation using X-AIGD provides several key insights: (1) Existing AIGI detectors demonstrate negligible reliance on perceptual artifacts, even at the most basic distortion level. (2) While AIGI detectors can be trained to identify specific artifacts, they still substantially base their judgment on uninterpretable features. (3) Explicitly aligning model attention with artifact regions can increase the interpretability and generalization of detectors. The data and code are available at: https://github.com/Coxy7/X-AIGD.
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。
