Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation
This work addresses the need for explainability in face recognition for security-critical applications, providing tools to increase trust and accountability, though it is incremental as it builds on existing methods with a focus on efficiency and benchmarking.
The authors tackled the problem of explaining face verification decisions by proposing xSSAB, a method that back-propagates similarity score arguments to visualize spatial maps indicating similar and dissimilar areas, and introduced Patch-LFW, a new benchmark for quantitative evaluation, demonstrating a superior trade-off between efficiency and performance.
Explainable Face Recognition is gaining growing attention as the use of the technology is gaining ground in security-critical applications. Understanding why two faces images are matched or not matched by a given face recognition system is important to operators, users, anddevelopers to increase trust, accountability, develop better systems, and highlight unfair behavior. In this work, we propose xSSAB, an approach to back-propagate similarity score-based arguments that support or oppose the face matching decision to visualize spatial maps that indicate similar and dissimilar areas as interpreted by the underlying FR model. Furthermore, we present Patch-LFW, a new explainable face verification benchmark that enables along with a novel evaluation protocol, the first quantitative evaluation of the validity of similarity and dissimilarity maps in explainable face recognition approaches. We compare our efficient approach to state-of-the-art approaches demonstrating a superior trade-off between efficiency and performance. The code as well as the proposed Patch-LFW is publicly available at: https://github.com/marcohuber/xSSAB.