Generalize Your Face Forgery Detectors: An Insertable Adaptation Module Is All You Need
원문 초록
A plethora of face forgery detectors exist to tackle facial deepfake risks. However, their practical application is hindered by the challenge of generalizing to forgeries unseen during the training stage. To this end, we introduce an insertable adaptation module that can adapt a trained off-the-shelf detector using only online unlabeled test data, without requiring modifications to the architecture or training process. Specifically, we first present a learnable class prototype-based classifier that generates predictions from the revised features and prototypes, enabling effective handling of various forgery clues and domain gaps during online testing. Additionally, we propose a nearest feature calibrator to further improve prediction accuracy and reduce the impact of noisy pseudo-labels during self-training. Experiments across multiple datasets show that our module achieves superior generalization compared to state-of-the-art methods. Moreover, it functions as a plug-and-play component that can be combined with various detectors to enhance the overall performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception
Is Diversity All You Need for Scalable Robotic Manipulation?
Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
토론
이 논문과 연결된 포럼 글이 아직 없습니다.