Rama Chellappa

Convolutional neural networks for attribute-based active authentication on mobile devices

2016

We present a Deep Convolutional Neural Network (DCNN) architecture for the task of continuous authentication on mobile devices. To deal with the limited resources of these devices, we reduce the complexity of the networks by …

Generate to Adapt: Aligning Domains Using Generative Adversarial Networks

2018

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. …

Continuous Authentication of Smartphones Based on Application Usage

2018 · arXiv (Cornell University)

An empirical investigation of active/continuous authentication for smartphones is presented in this paper by exploiting users' unique application usage data, i.e., distinct patterns of use, modeled by a Markovian process. Variations of Hidden Markov Models …

Wasserstein Distance Based Domain Adaptation for Object Detection

2019 · arXiv (Cornell University)

In this paper, we present an adversarial unsupervised domain adaptation framework for object detection. Prior approaches utilize adversarial training based on cross entropy between the source and target domain distributions to learn a shared feature …