Search Results for author:
Found 55 papers, 15 papers with code
Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications
With the rapid adoption of machine learning techniques for large-scale applications in science and engineering comes the convergence of two grand challenges in visualization.
Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
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.
Parallelizing Training of Deep Generative Models on Massive Scientific Datasets
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.
Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion.
Unsupervised Audio Source Separation using Generative Priors
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.
Improving Diversity with Adversarially Learned Transformations for Domain Generalization
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies.
Out of Distribution Detection via Neural Network Anchoring
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
Single Model Uncertainty Estimation via Stochastic Data Centering
We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems.
A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams
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.
Elastic Functional Coding of Riemannian Trajectories
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.
Function Preserving Projection for Scalable Exploration of High-Dimensional Data
We present function preserving projections (FPP), a scalable linear projection technique for discovering interpretable relationships in high-dimensional data.
Generative Patch Priors for Practical Compressive Image Recovery
In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models.
Attribute-Guided Adversarial Training for Robustness to Natural Perturbations
While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes.
CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction
In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations.
Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
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.
An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
We solve this by making successive estimates on the model and the solution in an iterative fashion.
Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$ view of the object.
MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis
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
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.
Autism Spectrum Disorder Classification using Graph Kernels on Multidimensional Time Series
We present an approach to model time series data from resting state fMRI for autism spectrum disorder (ASD) severity classification.
Diversity Promoting Online Sampling for Streaming Video Summarization
In this paper, we use diverse sampling for streaming video summarization.
Geometry-based Adaptive Symbolic Approximation for Fast Sequence Matching on Manifolds
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.
Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data
To this end, we present the first system that estimates detector performance interactively without extensive ground truthing using a human in the loop.
Unsupervised Dimension Selection using a Blue Noise Spectrum
Unsupervised dimension selection is an important problem that seeks to reduce dimensionality of data, while preserving the most useful characteristics.
Understanding Deep Neural Networks through Input Uncertainties
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.
Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense
Solving inverse problems continues to be a central challenge in computer vision.
MR-GAN: Manifold Regularized Generative Adversarial Networks
Despite the growing interest in generative adversarial networks (GANs), training GANs remains a challenging problem, both from a theoretical and a practical standpoint.
Elastic Functional Coding of Human Actions: From Vector-Fields to Latent Variables
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.
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
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.
Improving Limited Angle CT Reconstruction with a Robust GAN Prior
Limited angle CT reconstruction is an under-determined linear inverse problem that requires appropriate regularization techniques to be solved.
Extreme Few-view CT Reconstruction using Deep Inference
Reconstruction of few-view x-ray Computed Tomography (CT) data is a highly ill-posed problem.
Enabling Machine Learning-Ready HPC Ensembles with Merlin
With the growing complexity of computational and experimental facilities, many scientific researchers are turning to machine learning (ML) techniques to analyze large scale ensemble data.
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
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.
Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
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.
Accurate and Robust Feature Importance Estimation under Distribution Shifts
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.
Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates
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.
Machine Learning-Powered Mitigation Policy Optimization in Epidemiological Models
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.
Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
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.
Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization
Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis.
Suppressing simulation bias using multi-modal data
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.
Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields
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.
$Δ$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization
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.
A Biology-Informed Similarity Metric for Simulated Patches of Human Cell Membrane
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.
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion.
Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation
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.
Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers.
Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification
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.
On-the-fly Object Detection using StyleGAN with CLIP Guidance
We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention.
DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction
Limited-Angle Computed Tomography (LACT) is a non-destructive evaluation technique used in a variety of applications ranging from security to medicine.
PAGER: A Framework for Failure Analysis of Deep Regression Models
In this paper, we propose PAGER (Principled Analysis of Generalization Errors in Regressors), a framework to systematically detect and characterize failures in deep regression models.
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI).
Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains.
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
While graph neural networks (GNNs) are widely used for node and graph representation learning tasks, the reliability of GNN uncertainty estimates under distribution shifts remains relatively under-explored.
`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image.
