no code implementations • CVPR 2022 • Prithviraj Dhar, Amit Kumar, Kirsten Kaplan, Khushi Gupta, Rakesh Ranjan, Rama Chellappa
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.
no code implementations • 17 Dec 2021 • Prithviraj Dhar, Joshua Gleason, Aniket Roy, Carlos D. Castillo, P. Jonathon Phillips, Rama Chellappa
In D&D, we train a teacher network on images from one category of an attribute; e. g. light skintone.
no code implementations • ICCV 2021 • Prithviraj Dhar, Joshua Gleason, Aniket Roy, Carlos D. Castillo, Rama Chellappa
We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface.
no code implementations • 14 Jun 2020 • Prithviraj Dhar, Joshua Gleason, Hossein Souri, Carlos D. Castillo, Rama Chellappa
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.
no code implementations • 14 Feb 2020 • Connor J. Parde, Y. Ivette Colón, Matthew Q. Hill, Carlos D. Castillo, Prithviraj Dhar, Alice J. O'Toole
Therefore, distributed and sparse codes co-exist in the network units to represent different face attributes.
no code implementations • 12 Oct 2019 • Prithviraj Dhar, Ankan Bansal, Carlos D. Castillo, Joshua Gleason, P. Jonathon Phillips, Rama Chellappa
In the final fully connected layer of the networks, we found the order of expressivity for facial attributes to be Age > Sex > Yaw.
no code implementations • 4 Mar 2019 • Prithviraj Dhar, Carlos D. Castillo, Rama Chellappa
For a given identity in a face dataset, there are certain iconic images which are more representative of the subject than others.
1 code implementation • CVPR 2019 • Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng, Ziyan Wu, Rama Chellappa
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.