Improved Xception with Dual Attention Mechanism and Feature Fusion for Face Forgery Detection
This work addresses the challenge of face forgery detection for social media security, but it is incremental as it builds upon the Xception architecture with attention and fusion techniques.
The paper tackles the problem of detecting low-quality or diverse-source deepfake face forgeries by proposing an improved Xception model with dual attention mechanisms and feature fusion, achieving superior performance and generalization on three Deepfake datasets compared to existing methods.
With the rapid development of deep learning technology, more and more face forgeries by deepfake are widely spread on social media, causing serious social concern. Face forgery detection has become a research hotspot in recent years, and many related methods have been proposed until now. For those images with low quality and/or diverse sources, however, the detection performances of existing methods are still far from satisfactory. In this paper, we propose an improved Xception with dual attention mechanism and feature fusion for face forgery detection. Different from the middle flow in original Xception model, we try to catch different high-semantic features of the face images using different levels of convolution, and introduce the convolutional block attention module and feature fusion to refine and reorganize those high-semantic features. In the exit flow, we employ the self-attention mechanism and depthwise separable convolution to learn the global information and local information of the fused features separately to improve the classification the ability of the proposed model. Experimental results evaluated on three Deepfake datasets demonstrate that the proposed method outperforms Xception as well as other related methods both in effectiveness and generalization ability.