Interpretable Face Manipulation Detection via Feature Whitening
This addresses the need for transparency in deep neural networks for face manipulation detection, which is important for improving fairness, reliability, privacy, and trust, though it appears incremental as it builds on existing detection methods.
The paper tackles the problem of making face manipulation detection trustworthy by proposing an interpretable approach that embeds a feature whitening module to decorrelate and constrain features, achieving a balance between detection accuracy and model interpretability.
Why should we trust the detections of deep neural networks for manipulated faces? Understanding the reasons is important for users in improving the fairness, reliability, privacy and trust of the detection models. In this work, we propose an interpretable face manipulation detection approach to achieve the trustworthy and accurate inference. The approach could make the face manipulation detection process transparent by embedding the feature whitening module. This module aims to whiten the internal working mechanism of deep networks through feature decorrelation and feature constraint. The experimental results demonstrate that our proposed approach can strike a balance between the detection accuracy and the model interpretability.