Exposing Deepfakes using Dual-Channel Network with Multi-Axis Attention and Frequency Analysis

This paper proposes a dual-channel network for DeepFake detection. The network comprises two channels: one using a stacked Maxvit block to process the downsampled original images, and the other using a stacked ResNet basic block to capture features from the discrete cosine transform of the image spectrums. The components extracted from the two channels are concatenated using a linear layer to train the entire model for exposing DeepFakes. Experimental results demonstrate that the proposed method could achieve satisfactory forensics performance. Besides, the experiments of cross-dataset evaluations prove it is also high in generalizability.