To overcome this, we propose Eye Authentication with PAD (EyePAD), a distillation-based method that trains a single network for EA and PAD while reducing the effect of forgetting.
In D&D, we train a teacher network on images from one category of an attribute; e. g. light skintone.
We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface.
Therefore, we present a novel `Adversarial Gender De-biasing algorithm (AGENDA)' to reduce the gender information present in face descriptors obtained from previously trained face recognition networks.
Therefore, distributed and sparse codes co-exist in the network units to represent different face attributes.
In the final fully connected layer of the networks, we found the order of expressivity for facial attributes to be Age > Sex > Yaw.
Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model.