An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification
This provides incremental improvements for researchers and practitioners in biometrics by making CNN-based verification more interpretable.
The paper tackled the problem of adapting LIME for explainability in biometric verification, where classes are unseen during training and softmax outputs are not used, by modifying it to use cosine similarity between feature vectors; it demonstrated this on face biometrics with MobileNetv2 and ResNet50 models.
This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for training, and it employs the softmax probability to determine which regions of the image contribute the most to classification. However, in a verification setting, the classes to be recognized have not been seen during training. In addition, instead of using the softmax output, face descriptors are usually obtained from a layer before the classification layer. The model is adapted to achieve explainability via cosine similarity between feature vectors of perturbated versions of the input image. The method is showcased for face biometrics with two CNN models based on MobileNetv2 and ResNet50.