activity
20182021
most citedSingle Unit Status in Deep Convolutional Neural Network Codes for Face Identification: Sparseness Redefined

9 citations · 19 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2021

PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

Prithviraj Dhar, Joshua Gleason, Aniket Roy +2

Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face r…

cs.CV20209 cited

Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition

Prithviraj Dhar, Joshua Gleason, Hossein Souri +2

State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to ident…

cs.CV20209 cited

Single Unit Status in Deep Convolutional Neural Network Codes for Face Identification: Sparseness Redefined

Connor J. Parde, Y. Ivette Colón, Matthew Q. Hill +3

Deep convolutional neural networks (DCNNs) trained for face identification develop representations that generalize over variable images, while retaining subject (e.g., gender) and…

cs.CV2019

How are attributes expressed in face DCNNs?

Prithviraj Dhar, Ankan Bansal, Carlos D. Castillo +3

As deep networks become increasingly accurate at recognizing faces, it is vital to understand how these networks process faces. While these networks are solely trained to recognize…

cs.CV20191 cited

On measuring the iconicity of a face

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. In this paper, we explore the problem of computing…

cs.CV2018

Learning without Memorizing

Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng +2

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. The key problem i…