Search Results for author: Kumar Sricharan

Found 8 papers, 1 papers with code

Improving robustness of classifiers by training against live traffic

no code implementations1 Dec 2018 Kumar Sricharan, Kumar Kallurupalli, Ashok Srivastava

In this paper, we make the following observation: in practice, the out of distribution samples are contained in the traffic that hits a deployed classifier.

Building robust classifiers through generation of confident out of distribution examples

no code implementations1 Dec 2018 Kumar Sricharan, Ashok Srivastava

There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples.

ExprGAN: Facial Expression Editing with Controllable Expression Intensity

2 code implementations12 Sep 2017 Hui Ding, Kumar Sricharan, Rama Chellappa

To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity.

Data Augmentation Image Retrieval +2

Semi-supervised Conditional GANs

no code implementations19 Aug 2017 Kumar Sricharan, Raja Bala, Matthew Shreve, Hui Ding, Kumar Saketh, Jin Sun

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework.

Recognizing Abnormal Heart Sounds Using Deep Learning

no code implementations14 Jul 2017 Jonathan Rubin, Rui Abreu, Anurag Ganguli, Saigopal Nelaturi, Ion Matei, Kumar Sricharan

The work presented here applies deep learning to the task of automated cardiac auscultation, i. e. recognizing abnormalities in heart sounds.

Specificity

Latent Laplacian Maximum Entropy Discrimination for Detection of High-Utility Anomalies

no code implementations16 Feb 2017 Elizabeth Hou, Kumar Sricharan, Alfred O. Hero

Data-driven anomaly detection methods suffer from the drawback of detecting all instances that are statistically rare, irrespective of whether the detected instances have real-world significance or not.

Unsupervised Anomaly Detection

Ensemble weighted kernel estimators for multivariate entropy estimation

no code implementations NeurIPS 2012 Kumar Sricharan, Alfred O. Hero

In this paper, it is shown that for sufficiently smooth densities, an ensemble of kernel plug-in estimators can be combined via a weighted convex combination, such that the resulting weighted estimator has a superior parametric MSE rate of convergence of order $O(T^{-1})$.

Efficient anomaly detection using bipartite k-NN graphs

no code implementations NeurIPS 2011 Kumar Sricharan, Alfred O. Hero

In this paper, we propose a novel bipartite k-nearest neighbor graph (BP-kNNG) anomaly detection scheme for estimating minimum volume sets.

Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.