Search Results for author: Rushil Anirudh

Found 49 papers, 13 papers with code

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models

no code implementations CVPR 2023 Matthew L. Olson, Shusen Liu, Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Weng-Keen Wong

To this end, we introduce Cross-GAN Auditing (xGA) that, given an established "reference" GAN and a newly proposed "client" GAN, jointly identifies intelligible attributes that are either common across both GANs, novel to the client GAN, or missing from the client GAN.


DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction

no code implementations22 Nov 2022 Jiaming Liu, Rushil Anirudh, Jayaraman J. Thiagarajan, Stewart He, K. Aditya Mohan, Ulugbek S. Kamilov, Hyojin Kim

Limited-Angle Computed Tomography (LACT) is a non-destructive evaluation technique used in a variety of applications ranging from security to medicine.

On-the-fly Object Detection using StyleGAN with CLIP Guidance

no code implementations30 Oct 2022 Yuzhe Lu, Shusen Liu, Jayaraman J. Thiagarajan, Wesam Sakla, Rushil Anirudh

We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention.

object-detection Object Detection

Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification

no code implementations25 Jul 2022 Rakshith Subramanyam, Mark Heimann, Jayram Thathachar, Rushil Anirudh, Jayaraman J. Thiagarajan

Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples.

Classification Few-Shot Learning

Single Model Uncertainty Estimation via Stochastic Data Centering

1 code implementation14 Jul 2022 Jayaraman J. Thiagarajan, Rushil Anirudh, Vivek Narayanaswamy, Peer-Timo Bremer

We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems.

Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors

no code implementations12 Jul 2022 Vivek Narayanaswamy, Yamen Mubarka, Rushil Anirudh, Deepta Rajan, Andreas Spanias, Jayaraman J. Thiagarajan

We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers.

Data Augmentation Open Set Learning +3

Out of Distribution Detection via Neural Network Anchoring

3 code implementations8 Jul 2022 Rushil Anirudh, Jayaraman J. Thiagarajan

Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Improving Diversity with Adversarially Learned Transformations for Domain Generalization

1 code implementation15 Jun 2022 Tejas Gokhale, Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Chitta Baral, Yezhou Yang

To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies.

Domain Generalization

Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation

no code implementations5 Jan 2022 Kowshik Thopalli, Jayaraman J Thiagarajan, Rushil Anirudh, Pavan K Turaga

In contrast to existing adversarial training-based DA methods, our approach isolates feature learning and distribution alignment steps, and utilizes a primary-auxiliary optimization strategy to effectively balance the objectives of domain invariance and model fidelity.

Representation Learning Unsupervised Domain Adaptation

Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion

no code implementations24 Nov 2021 Ankita Shukla, Rushil Anirudh, Eugene Kur, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Brian K. Spears, Tammy Ma, Pavan Turaga

In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion.

$Δ$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization

no code implementations5 Oct 2021 Rushil Anirudh, Jayaraman J. Thiagarajan

Anchoring works by first transforming the input into a tuple consisting of an anchor point drawn from a prior distribution, and a combination of the input sample with the anchor using a pretext encoding scheme.

Model Optimization Out-of-Distribution Detection

A Biology-Informed Similarity Metric for Simulated Patches of Human Cell Membrane

no code implementations29 Sep 2021 Harsh Bhatia, Jayaraman J. Thiagarajan, Rushil Anirudh, T.S. Jayram, Tomas Oppelstrup, Helgi I. Ingolfsson, Felice C Lightstone, Peer-Timo Bremer

Complex scientific inquiries rely increasingly upon large and autonomous multiscale simulation campaigns, which fundamentally require similarity metrics to quantify "sufficient'' changes among data and/or configurations.

Metric Learning

Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields

no code implementations ICCV 2021 Albert W. Reed, Hyojin Kim, Rushil Anirudh, K. Aditya Mohan, Kyle Champley, Jingu Kang, Suren Jayasuriya

However, if the scene is moving too fast, then the sampling occurs along a limited view and is difficult to reconstruct due to spatiotemporal ambiguities.

Suppressing simulation bias using multi-modal data

no code implementations19 Apr 2021 Bogdan Kustowski, Jim A. Gaffney, Brian K. Spears, Gemma J. Anderson, Rushil Anirudh, Peer-Timo Bremer, Jayaraman J. Thiagarajan, Michael K. G. Kruse, Ryan C. Nora

The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.

Transfer Learning

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations

3 code implementations3 Dec 2020 Tejas Gokhale, Rushil Anirudh, Bhavya Kailkhura, Jayaraman J. Thiagarajan, Chitta Baral, Yezhou Yang

While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes.

Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization

no code implementations3 Dec 2020 Suhas Lohit, Rushil Anirudh, Pavan Turaga

Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis.

Action Recognition

Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations

no code implementations26 Oct 2020 Gemma J. Anderson, Jim A. Gaffney, Brian K. Spears, Peer-Timo Bremer, Rushil Anirudh, Jayaraman J. Thiagarajan

Large-scale numerical simulations are used across many scientific disciplines to facilitate experimental development and provide insights into underlying physical processes, but they come with a significant computational cost.

Variational Inference

Machine Learning-Powered Mitigation Policy Optimization in Epidemiological Models

no code implementations16 Oct 2020 Jayaraman J. Thiagarajan, Peer-Timo Bremer, Rushil Anirudh, Timothy C. Germann, Sara Y. Del Valle, Frederick H. Streitz

A crucial aspect of managing a public health crisis is to effectively balance prevention and mitigation strategies, while taking their socio-economic impact into account.

BIG-bench Machine Learning

Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates

no code implementations13 Oct 2020 Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Timothy C. Germann, Sara Y. Del Valle, Frederick H. Streitz

Here we present a new approach to calibrate an agent-based model -- EpiCast -- using a large set of simulation ensembles for different major metropolitan areas of the United States.

Accurate and Robust Feature Importance Estimation under Distribution Shifts

no code implementations30 Sep 2020 Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Rushil Anirudh, Peer-Timo Bremer, Andreas Spanias

With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models.

Feature Importance

Generative Patch Priors for Practical Compressive Image Recovery

1 code implementation18 Jun 2020 Rushil Anirudh, Suhas Lohit, Pavan Turaga

In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models.

Compressive Sensing Image Reconstruction +1

Unsupervised Audio Source Separation using Generative Priors

1 code implementation28 May 2020 Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Rushil Anirudh, Andreas Spanias

State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain.

Audio Source Separation

Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models

no code implementations5 May 2020 Jayaraman J. Thiagarajan, Bindya Venkatesh, Rushil Anirudh, Peer-Timo Bremer, Jim Gaffney, Gemma Anderson, Brian Spears

Predictive models that accurately emulate complex scientific processes can achieve exponential speed-ups over numerical simulators or experiments, and at the same time provide surrogates for improving the subsequent analysis.

Small Data Image Classification

Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies

1 code implementation17 Dec 2019 Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer, Brian K. Spears

Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion.

MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking

no code implementations16 Dec 2019 Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer

However, PGD is a brittle optimization technique that fails to identify the right projection (or latent vector) when the observation is corrupted, or perturbed even by a small amount.

Adversarial Defense Anomaly Detection +2

Parallelizing Training of Deep Generative Models on Massive Scientific Datasets

2 code implementations5 Oct 2019 Sam Ade Jacobs, Brian Van Essen, David Hysom, Jae-Seung Yeom, Tim Moon, Rushil Anirudh, Jayaraman J. Thiagaranjan, Shusen Liu, Peer-Timo Bremer, Jim Gaffney, Tom Benson, Peter Robinson, Luc Peterson, Brian Spears

Training deep neural networks on large scientific data is a challenging task that requires enormous compute power, especially if no pre-trained models exist to initialize the process.

Improving Limited Angle CT Reconstruction with a Robust GAN Prior

no code implementations NeurIPS Workshop Deep_Invers 2019 Rushil Anirudh, Hyojin Kim, Jayaraman J. Thiagarajan, K. Aditya Mohan, Kyle M. Champley

Limited angle CT reconstruction is an under-determined linear inverse problem that requires appropriate regularization techniques to be solved.

Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion

2 code implementations3 Oct 2019 Rushil Anirudh, Jayaraman J. Thiagarajan, Shusen Liu, Peer-Timo Bremer, Brian K. Spears

There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-driven fashion.

Function Preserving Projection for Scalable Exploration of High-Dimensional Data

1 code implementation25 Sep 2019 Shusen Liu, Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer

We present function preserving projections (FPP), a scalable linear projection technique for discovering interpretable relationships in high-dimensional data.

Dimensionality Reduction Vocal Bursts Intensity Prediction

SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation

no code implementations11 Jun 2019 Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh, Pavan Turaga

This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source.

Auxiliary Learning Unsupervised Domain Adaptation

MR-GAN: Manifold Regularized Generative Adversarial Networks

no code implementations22 Nov 2018 Qunwei Li, Bhavya Kailkhura, Rushil Anirudh, Yi Zhou, Yingbin Liang, Pramod Varshney

Despite the growing interest in generative adversarial networks (GANs), training GANs remains a challenging problem, both from a theoretical and a practical standpoint.

Understanding Deep Neural Networks through Input Uncertainties

no code implementations31 Oct 2018 Jayaraman J. Thiagarajan, Irene Kim, Rushil Anirudh, Peer-Timo Bremer

Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract new insights about the data via exploratory analysis.

Unsupervised Dimension Selection using a Blue Noise Spectrum

no code implementations31 Oct 2018 Jayaraman J. Thiagarajan, Rushil Anirudh, Rahul Sridhar, Peer-Timo Bremer

Unsupervised dimension selection is an important problem that seeks to reduce dimensionality of data, while preserving the most useful characteristics.

Dimensionality Reduction

MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis

no code implementations15 Nov 2017 Rushil Anirudh, Jayaraman J. Thiagarajan, Rahul Sridhar, Peer-Timo Bremer

Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user.

Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification

no code implementations24 Apr 2017 Rushil Anirudh, Jayaraman J. Thiagarajan

To address this, we propose a bootstrapped version of graph convolutional neural networks (G-CNNs) that utilizes an ensemble of weakly trained G-CNNs, and reduce the sensitivity of models on the choice of graph construction.

Classification General Classification +1

Autism Spectrum Disorder Classification using Graph Kernels on Multidimensional Time Series

no code implementations29 Nov 2016 Rushil Anirudh, Jayaraman J. Thiagarajan, Irene Kim, Wolfgang Polonik

We present an approach to model time series data from resting state fMRI for autism spectrum disorder (ASD) severity classification.

General Classification Time Series Analysis

A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams

1 code implementation28 May 2016 Rushil Anirudh, Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga

This paper concerns itself with one popular topological feature, which is the number of $d-$dimensional holes in the dataset, also known as the Betti$-d$ number.

Topological Data Analysis

Elastic Functional Coding of Riemannian Trajectories

1 code implementation7 Mar 2016 Rushil Anirudh, Pavan Turaga, Jingyong Su, Anuj Srivastava

We propose to learn an embedding such that each action trajectory is mapped to a single point in a low-dimensional Euclidean space, and the trajectories that differ only in temporal rates map to the same point.

Action Analysis Retrieval

Elastic Functional Coding of Human Actions: From Vector-Fields to Latent Variables

no code implementations CVPR 2015 Rushil Anirudh, Pavan Turaga, Jingyong Su, Anuj Srivastava

Learning an accurate low dimensional embedding for actions could have a huge impact in the areas of efficient search and retrieval, visualization, learning, and recognition.

Action Recognition Retrieval +1

Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data

no code implementations21 Jun 2014 Rushil Anirudh, Pavan Turaga

To this end, we present the first system that estimates detector performance interactively without extensive ground truthing using a human in the loop.

Geometry-based Adaptive Symbolic Approximation for Fast Sequence Matching on Manifolds

no code implementations4 Mar 2014 Rushil Anirudh, Pavan Turaga

This problem has several applications in the areas of human activity analysis, where there is a need to perform fast search, and recognition in very high dimensional spaces.

Activity Recognition Dynamic Texture Recognition

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