论文标题
一种在现实条件下改善基于学习的深层检测的新方法
A New Approach to Improve Learning-based Deepfake Detection in Realistic Conditions
论文作者
论文摘要
深度卷积神经网络已经在多个检测和识别任务上取得了出色的结果。但是，在有限和非现实情况下，经常在公共基准中评估此类探测器的性能。在诸如压缩，噪声和增强之类的成像工作流程中发现的常规扭曲和处理操作的影响尚未充分研究。目前，仅进行了少量研究以改善检测器的鲁棒性，以使其无法看见。本文提出了基于现实世界图像降级过程的更有效的数据增强方案。这种新颖的技术是为了进行深层检测任务而部署的，并通过更现实的评估框架进行了评估。广泛的实验表明，所提出的数据增强方案提高了通用能力，使其无法预测的数据扭曲和看不见的数据集。
Deep convolutional neural networks have achieved exceptional results on multiple detection and recognition tasks. However, the performance of such detectors are often evaluated in public benchmarks under constrained and non-realistic situations. The impact of conventional distortions and processing operations found in imaging workflows such as compression, noise, and enhancement are not sufficiently studied. Currently, only a few researches have been done to improve the detector robustness to unseen perturbations. This paper proposes a more effective data augmentation scheme based on real-world image degradation process. This novel technique is deployed for deepfake detection tasks and has been evaluated by a more realistic assessment framework. Extensive experiments show that the proposed data augmentation scheme improves generalization ability to unpredictable data distortions and unseen datasets.
