Evaluating Facial Recognition Technology: A Protocol for Performance Assessment in New Domains
In May 2020, Stanford's HAI hosted a workshop to discuss the performance of facial recognition technologies that included leading computer scientists, legal scholars, and representatives from industry, government, and civil society. The white paper this workshop produced seeks to answer key questions in improving understandings of this rapidly changing space.
The Stanford HAI white paper outlines a protocol for evaluating facial recognition technology (FRT) performance in new domains, stressing the importance of rigorous, context-specific accuracy assessments over vendor-reported benchmarks.
It highlights domain shift and institutional shift as primary sources of performance issues and recommends transparency in training data, in-domain testing, ongoing documentation, and human-centered evaluation methods to ensure responsible deployment and auditing of FRT.
Share this Resource:
