轻量级广义DeepFake人脸检测：WAVIE——小波增强视觉中间嵌入
Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Intermediate Embeddings
浏览论文内容
中文总结 AI 辅助
针对Deepfake检测跨数据集泛化差的问题，提出WAVIE架构，在冻结CLIP骨干上结合小波变换与中间嵌入，仅用FaceForensics++训练即在多个数据集上超越现有基线。
中文摘要 AI 辅助
Deepfake检测系统在部署到未见过的篡改方法上时，往往表现出显著的性能下降，这限制了它们在真实多媒体环境中的可靠性。这种泛化能力的缺失对错误信息缓解、数字取证和以人为中心的AI系统构成了严峻挑战。现有检测器在它们训练过的伪造方法上表现良好，但在未见过的流程上准确率急剧下降。为了弥合这一泛化差距，我们提出了WAVIE（小波增强视觉中间嵌入），一种端到端架构，在冻结的CLIP骨干之上结合了互补的空间和频率线索。WAVIE通过一个轻量级可学习模块投影中间Transformer嵌入，应用三级Daubechies-6（db6）离散小波变换（DWT），在保留高频分支的同时细化低频分支，通过逆DWT重建特征，并执行分类。仅在FaceForensics++上训练，WAVIE在帧级别上于Celeb-DF-v1上达到AUROC=0.852，于Celeb-DF-v2上达到0.852，于WildDeepFake（WDF）上达到0.831，超越了多个最先进的泛化基线。广泛的消融研究证实了小波模块和中间特征聚合对跨数据集性能的重要性，强调了联合利用空间和频率域的必要性。这些结果使WAVIE成为野外Deepfake检测的强有力基线。
英文摘要
Deepfake detection systems often exhibit significant performance degradation when deployed on unseen manipulation methods, limiting their reliability in real-world multimedia environments. This lack of generalization poses critical challenges for misinformation mitigation, digital forensics, and human-centric AI systems. Existing detectors perform well on the forgery methods they are trained on, but their accuracy drops sharply on unseen pipelines. To bridge this generalization gap, we propose WAVIE (Wavelet Augmented Vision Intermediate Embeddings), an end-to-end architecture that combines complementary spatial and frequency cues on top of a frozen CLIP backbone. WAVIE projects intermediate transformer embeddings through a lightweight learnable module, applies a three-level Daubechies-6 (db6) discrete wavelet transform (DWT), refines the low-frequency branch while preserving the high-frequency branch, reconstructs the feature via inverse DWT, and performs classification. Trained only on FaceForensics++, WAVIE achieves AUROC = 0.852 on Celeb-DF-v1, 0.852 on Celeb-DF-v2 and 0.831 on WildDeepFake (WDF) at the frame level, outperforming several state-of-the-art generalization baselines. Extensive ablation studies confirm the importance of both the wavelet module and the intermediate-feature aggregation for cross-dataset performance, highlighting the necessity of jointly leveraging spatial and frequency domains. These results position WAVIE as a strong baseline for deepfake detection in the wild.
发表机构
- School of Computing and Electrical Engineering, IIT Mandi（印度理工学院曼迪分校计算与电气工程学院）
- PHYTEC Messtechnik GmbH（PHYTEC测量技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。
