LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection

This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few small artifactprone vulnerable regions. Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy. Experiments performed on several benchmarks show the superiority of our approach in terms of Area Under the Curve (AUC) and Average Precision (AP). The code is available at https://github . com/10Ring/LAA-Net. Recent works have mostly focused on improving the generalization capabilities of deepfake detection methods by adopting multi-task learning [7, 24, 54] and/or heuris-This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.