Explaining Deep Face Algorithms through Visualization: A Survey
It addresses the lack of understanding and potential biases in deep face algorithms, offering guidance for AI practitioners, but is incremental as it surveys and adapts existing methods.
The paper conducts a meta-analysis of explainability algorithms for deep face models, exploring adaptations of general-purpose visualization methods to the face domain and providing insights into network structure and practical design considerations through a user study.
Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work. Thus, we cannot predict how it will react to novel inputs, resulting in catastrophic failures and unwanted biases in the algorithms. Explainable AI helps bridge the gap, but currently, there are very few visualization algorithms designed for faces. This work undertakes a first-of-its-kind meta-analysis of explainability algorithms in the face domain. We explore the nuances and caveats of adapting general-purpose visualization algorithms to the face domain, illustrated by computing visualizations on popular face models. We review existing face explainability works and reveal valuable insights into the structure and hierarchy of face networks. We also determine the design considerations for practical face visualizations accessible to AI practitioners by conducting a user study on the utility of various explainability algorithms.