通过频率一致性机制，提升伪造检测模型对新型伪造的泛化能力。
FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
- 引入频域混合增强与双一致性正则，减少模型对特定频率的依赖。
- 在跨域和同域测试中均超越现有最佳方法，显著提升泛化性能。
- 适合需要高鲁棒性伪造检测的应用场景，如社交媒体内容审核。
深度伪造检测模型常因训练数据有限而难以泛化到新型伪造。本文发现一种新的频域偏差——谱偏差，即检测器过度依赖特定频率带，限制了对未知伪造的适应能力。为此提出FreqDebias框架，采用两种互补策略：一是新颖的伪造混合增强（Fo-Mixup），动态丰富训练样本的频率特征；二是双一致性正则（CR），通过类激活图实现局部一致性，并在超球嵌入空间中使用冯·米塞斯-费舍尔分布实现全局一致性，从而抑制对特定频率成分的过拟合。大量实验表明，FreqDebias显著提升跨域泛化能力，在跨域与同域设置下均优于现有最优方法。
原文摘要 · Abstract (English)
Deepfake detectors often struggle to generalize to novel forgery types due to biases learned from limited training data. In this paper, we identify a new type of model bias in the frequency domain, termed spectral bias, where detectors overly rely on specific frequency bands, restricting their ability to generalize across unseen forgeries. To address this, we propose FreqDebias, a frequency debiasing framework that mitigates spectral bias through two complementary strategies. First, we introduce a novel Forgery Mixup (Fo-Mixup) augmentation, which dynamically diversifies frequency characteristics of training samples. Second, we incorporate a dual consistency regularization (CR), which enforces both local consistency using class activation maps (CAMs) and global consistency through a von Mises-Fisher (vMF) distribution on a hyperspherical embedding space. This dual CR mitigates over-reliance on certain frequency components by promoting consistent representation learning under both local and global supervision. Extensive experiments show that FreqDebias significantly enhances cross-domain generalization and outperforms state-of-the-art methods in both cross-domain and in-domain settings.
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。