Explainable Face Verification via Feature-Guided Gradient Backpropagation
This work addresses the need for reliable interpretations in face recognition systems, which are critical for security-sensitive applications, by providing an incremental improvement over existing explanation methods.
The paper tackles the problem of explaining face verification decisions by proposing FGGB, a feature-guided gradient backpropagation method that generates similarity and dissimilarity saliency maps, achieving superior performance compared to state-of-the-art approaches in both visual and quantitative evaluations.
Recent years have witnessed significant advancement in face recognition (FR) techniques, with their applications widely spread in people's lives and security-sensitive areas. There is a growing need for reliable interpretations of decisions of such systems. Existing studies relying on various mechanisms have investigated the usage of saliency maps as an explanation approach, but suffer from different limitations. This paper first explores the spatial relationship between face image and its deep representation via gradient backpropagation. Then a new explanation approach FGGB has been conceived, which provides precise and insightful similarity and dissimilarity saliency maps to explain the "Accept" and "Reject" decision of an FR system. Extensive visual presentation and quantitative measurement have shown that FGGB achieves superior performance in both similarity and dissimilarity maps when compared to current state-of-the-art explainable face verification approaches.