173 citations · 504 across the 54 of their papers we have counts for
69 papers
Domain Alignment Meets Fully Test-Time Adaptation
Kowshik Thopalli, Pavan Turaga, Jayaraman J. Thiagarajan
A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is…
Designing Counterfactual Generators using Deep Model Inversion
Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan +3
Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting b…
MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation
Alexandros Karargyris, Renato Umeton, Micah J. Sheller +39
Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving prov…
On the Design of Deep Priors for Unsupervised Audio Restoration
Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for definin…
Loss Estimators Improve Model Generalization
Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Deepta Rajan +1
With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate pre…
Comparative Code Structure Analysis using Deep Learning for Performance Prediction
Nathan Pinnow, Tarek Ramadan, Tanzima Z. Islam +2
Performance analysis has always been an afterthought during the application development process, focusing on application correctness first. The learning curve of the existing stati…
Attribute-Guided Adversarial Training for Robustness to Natural Perturbations
Tejas Gokhale, Rushil Anirudh, Bhavya Kailkhura +3
While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world sett…
Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
Gemma J. Anderson, Jim A. Gaffney, Brian K. Spears +3
Large-scale numerical simulations are used across many scientific disciplines to facilitate experimental development and provide insights into underlying physical processes, but th…
Using Deep Image Priors to Generate Counterfactual Explanations
Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias
Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. Th…
Machine Learning-Powered Mitigation Policy Optimization in Epidemiological Models
Jayaraman J. Thiagarajan, Peer-Timo Bremer, Rushil Anirudh +3
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. In partic…
Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates
Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer +3
Calibrating complex epidemiological models to observed data is a crucial step to provide both insights into the current disease dynamics, i.e.\ by estimating a reproductive number,…
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias
Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are e…
Accurate and Robust Feature Importance Estimation under Distribution Shifts
Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Rushil Anirudh +2
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 use…
Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
Bindya Venkatesh, Jayaraman J. Thiagarajan
Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and t…
Unsupervised Audio Source Separation using Generative Priors
Vivek Narayanaswamy, Jayaraman J. Thiagarajan, Rushil Anirudh +1
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 tim…
Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
Jayaraman J. Thiagarajan, Bindya Venkatesh, Rushil Anirudh +4
Predictive models that accurately emulate complex scientific processes can achieve exponential speed-ups over numerical simulators or experiments, and at the same time provide surr…
Self-Training with Improved Regularization for Sample-Efficient Chest X-Ray Classification
Deepta Rajan, Jayaraman J. Thiagarajan, Alexandros Karargyris +1
Automated diagnostic assistants in healthcare necessitate accurate AI models that can be trained with limited labeled data, can cope with severe class imbalances and can support si…
Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models
Jayaraman J. Thiagarajan, Prasanna Sattigeri, Deepta Rajan +1
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous…
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
Bindya Venkatesh, Jayaraman J. Thiagarajan, Kowshik Thopalli +1
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generaliza…
Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
Rushil Anirudh, Jayaraman J. Thiagarajan, Peer-Timo Bremer +1
Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion. This paper a…
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura +1
In the past few years, Generative Adversarial Networks (GANs) have dramatically advanced our ability to represent and parameterize high-dimensional, non-linear image manifolds. As…
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Sameeksha Katoch, Kowshik Thopalli, Jayaraman J. Thiagarajan +2
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization…
Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
Bindya Venkatesh, Jayaraman J. Thiagarajan
The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exi…
Learn-By-Calibrating: Using Calibration as a Training Objective
Jayaraman J. Thiagarajan, Bindya Venkatesh, Deepta Rajan
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial…