Search Results for author:
Found 8 papers, 1 papers with code
EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Images
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.
Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation
In D&D, we train a teacher network on images from one category of an attribute; e. g. light skintone.
PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition
We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface.
Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition
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.
Single Unit Status in Deep Convolutional Neural Network Codes for Face Identification: Sparseness Redefined
Therefore, distributed and sparse codes co-exist in the network units to represent different face attributes.
How are attributes expressed in face DCNNs?
In the final fully connected layer of the networks, we found the order of expressivity for facial attributes to be Age > Sex > Yaw.
On measuring the iconicity of a face
For a given identity in a face dataset, there are certain iconic images which are more representative of the subject than others.
Learning without Memorizing
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.
