论文标题
在现实条件下评估基于学习的探测器的新型框架，并应用了深层检测
A Novel Framework for Assessment of Learning-based Detectors in Realistic Conditions with Application to Deepfake Detection
论文作者
论文摘要
深度卷积神经网络在多个检测任务上显示出了显着的结果。尽管取得了重大进展，但在非现实条件下，经常在公共基准中评估此类探测器的性能。具体而言，未充分研究了常规扭曲和加工操作（例如压缩，噪声和增强）的影响。本文提出了一个严格的框架，以评估在更现实的情况下基于学习的探测器的性能。一个说明性的示例在深泡检测环境中显示。受评估结果的启发，设计了基于自然图像降解过程的数据增强策略，从而显着提高了两个深泡检测器的概括能力。
Deep convolutional neural networks have shown remarkable results on multiple detection tasks. Despite the significant progress, the performance of such detectors are often assessed in public benchmarks under non-realistic conditions. Specifically, impact of conventional distortions and processing operations such as compression, noise, and enhancement are not sufficiently studied. This paper proposes a rigorous framework to assess performance of learning-based detectors in more realistic situations. An illustrative example is shown under deepfake detection context. Inspired by the assessment results, a data augmentation strategy based on natural image degradation process is designed, which significantly improves the generalization ability of two deepfake detectors.
