Adaptive Frequency Learning in Two-branch Face Forgery Detection
This work addresses face forgery detection for security applications, representing an incremental improvement by adapting frequency decomposition and integration.
The paper tackles the problem of face forgery detection by proposing an adaptive frequency learning method within a two-branch framework, achieving improved performance over existing techniques.
Face forgery has attracted increasing attention in recent applications of computer vision. Existing detection techniques using the two-branch framework benefit a lot from a frequency perspective, yet are restricted by their fixed frequency decomposition and transform. In this paper, we propose to Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD. To be specific, we automatically learn decomposition in the frequency domain by introducing heterogeneity constraints, and propose an attention-based module to adaptively incorporate frequency features into spatial clues. Then we liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers. Extensive experiments show that AFD generally outperforms.