用FFT辅助的轻量模型提升深伪人脸检测准确率
SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection
- 基于EfficientNet-B6，结合数据增强与优化策略应对类别不平衡
- 在多个数据集上达到98%以上准确率，且泛化能力强
- 无需专业背景，适合非专家快速部署使用
检测深伪图像对遏制虚假信息至关重要。我们提出一种基于EfficientNet-B6的轻量级通用二分类模型，通过变换技术微调以应对严重的类别不平衡问题。借助稳健的预处理、过采样及优化策略，该模型实现了高精度、高稳定性和强泛化能力。尽管引入基于傅里叶变换的相位和幅度特征效果有限，但所提出的框架使非专业人士能有效识别深伪图像，在实现可访问、可靠的深伪检测方面迈出重要一步。
原文摘要 · Abstract (English)
Detecting deepfake images is crucial in combating misinformation. We present a lightweight, generalizable binary classification model based on EfficientNet-B6, fine-tuned with transformation techniques to address severe class imbalances. By leveraging robust preprocessing, oversampling, and optimization strategies, our model achieves high accuracy, stability, and generalization. While incorporating Fourier transform-based phase and amplitude features showed minimal impact, our proposed framework helps non-experts to effectively identify deepfake images, making significant strides toward accessible and reliable deepfake detection.
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。