Search Results for author: Pavan Turaga

Found 43 papers, 12 papers with code

Domain Alignment Meets Fully Test-Time Adaptation

1 code implementation9 Jul 2022 Kowshik Thopalli, Pavan Turaga, Jayaraman J. Thiagarajan

With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation.

Unsupervised Domain Adaptation

Deep Geometric Moment

no code implementations24 May 2022 Rajhans Singh, Ankita Shukla, Pavan Turaga

Deep networks for image classification often rely more on texture information than object shape.

Classification Image Classification

Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data

no code implementations1 Jan 2022 Eun Som Jeon, Anirudh Som, Ankita Shukla, Kristina Hasanaj, Matthew P. Buman, Pavan Turaga

In this paper, we report the results of a detailed study that compares and contrasts various common choices and some hybrid data augmentation strategies in KD based human activity analysis.

Data Augmentation Knowledge Distillation +1

Improving Multi-Domain Generalization through Domain Re-labeling

no code implementations17 Dec 2021 Kowshik Thopalli, Sameeksha Katoch, Andreas Spanias, Pavan Turaga, Jayaraman J. Thiagarajan

In this paper, we focus on the challenging problem of multi-source zero-shot DG, where labeled training data from multiple source domains is available but with no access to data from the target domain.

Domain Generalization

Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics

1 code implementation28 Nov 2021 John Kevin Cava, John Vant, Nicholas Ho, Ankita Shukla, Pavan Turaga, Ross Maciejewski, Abhishek Singharoy

In this paper, we utilized generative models, and reformulate it for problems in molecular dynamics (MD) simulation, by introducing an MD potential energy component to our generative model.

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.

Interpretable COVID-19 Chest X-Ray Classification via Orthogonality Constraint

no code implementations2 Feb 2021 Ella Y. Wang, Anirudh Som, Ankita Shukla, Hongjun Choi, Pavan Turaga

In addition to these findings, our work also presents a new application of the OS regularizer in healthcare, increasing the post-hoc interpretability and performance of deep learning models for COVID-19 classification to facilitate adoption of these methods in clinical settings.

Classification Data Augmentation +1

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

Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification

no code implementations22 Sep 2020 Hongjun Choi, Anirudh Som, Pavan Turaga

Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks.

General Classification Image Classification

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

GraCIAS: Grassmannian of Corrupted Images for Adversarial Security

no code implementations6 May 2020 Ankita Shukla, Pavan Turaga, Saket Anand

In this work, we propose a defense strategy that applies random image corruptions to the input image alone, constructs a self-correlation based subspace followed by a projection operation to suppress the adversarial perturbation.

AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification

1 code implementation21 Apr 2020 Hongjun Choi, Anirudh Som, Pavan Turaga

We find that although the proposed geometrically constrained loss-function improves quantitative results modestly, it has a qualitatively surprisingly beneficial effect on increasing the interpretability of deep-net decisions as seen by the visual explanations generated by techniques such as the Grad-CAM.

General Classification Image Classification

Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships

no code implementations18 Apr 2020 Kuldeep Kulkarni, Tejas Gokhale, Rajhans Singh, Pavan Turaga, Aswin Sankaranarayanan

The generated dense labelmap can then be used as input by state-of-the-art image synthesis techniques like pix2pixHD to obtain the final image.

Image Generation Semantic Segmentation

Topological Descriptors for Parkinson's Disease Classification and Regression Analysis

1 code implementation15 Apr 2020 Afra Nawar, Farhan Rahman, Narayanan Krishnamurthi, Anirudh Som, Pavan Turaga

In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessment.

Classification General Classification +1

Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning

no code implementations22 Jul 2019 Ankita Shukla, Sarthak Bhagat, Shagun Uppal, Saket Anand, Pavan Turaga

Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation.


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

PI-Net: A Deep Learning Approach to Extract Topological Persistence Images

1 code implementation5 Jun 2019 Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy, Matthew Buman, Pavan Turaga

To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.

Human Activity Recognition Image Classification +1

Non-Parametric Priors For Generative Adversarial Networks

no code implementations16 May 2019 Rajhans Singh, Pavan Turaga, Suren Jayasuriya, Ravi Garg, Martin W. Braun

The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging.

Data Augmentation Image Generation

Geometry of Deep Generative Models for Disentangled Representations

no code implementations19 Feb 2019 Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga

We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space.

Representation Learning

An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation

1 code implementation20 Dec 2018 Berkay Kanberoglu, Dhritiman Das, Priya Nair, Pavan Turaga, David Frakes

Three-dimensional (3D) biomedical image sets are often acquired with in-plane pixel spacings that are far less than the out-of-plane spacings between images.

Optical Flow Estimation

Rate-Adaptive Neural Networks for Spatial Multiplexers

no code implementations8 Sep 2018 Suhas Lohit, Rajhans Singh, Kuldeep Kulkarni, Pavan Turaga

Using standard datasets, we demonstrate that, when tested over a range of MRs, a rate-adaptive network can provide high quality reconstruction over a the entire range, resulting in up to about 15 dB improvement over previous methods, where the network is valid for only one MR. We demonstrate the effectiveness of our approach for sample-efficient object tracking where video frames are acquired at dynamically varying MRs. We also extend this algorithm to learn the measurement operator in conjunction with image recognition networks.

Object Tracking

Perturbation Robust Representations of Topological Persistence Diagrams

1 code implementation ECCV 2018 Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga

However, persistence diagrams are multi-sets of points and hence it is not straightforward to fuse them with features used for contemporary machine learning tools like deep-nets.

BIG-bench Machine Learning

Compressive Light Field Reconstructions using Deep Learning

no code implementations5 Feb 2018 Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni, Suren Jayasuriya, Alyosha Molnar, Pavan Turaga

We test our network reconstructions on synthetic light fields, simulated coded measurements of real light fields captured from a Lytro Illum camera, and real coded images from a custom CMOS diffractive light field camera.

Compressive Sensing

Learning Invariant Riemannian Geometric Representations Using Deep Nets

no code implementations30 Aug 2017 Suhas Lohit, Pavan Turaga

Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference.

BIG-bench Machine Learning Image Classification

Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images

no code implementations15 Aug 2017 Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan Turaga, Amit Ashok

We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise.

Compressive Sensing Object Tracking

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

Persistent Homology of Attractors For Action Recognition

no code implementations16 Mar 2016 Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga

In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis.

Action Recognition Time Series +1

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

Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference

no code implementations27 Jan 2016 Vinay Venkataraman, Pavan Turaga

Our experimental analyses on these models also indicate that the proposed framework show stability for different time-series lengths, which is useful when the available number of samples are small/variable.

Activity Recognition Gesture Recognition +2

Fast Integral Image Estimation at 1% measurement rate

no code implementations27 Jan 2016 Kuldeep Kulkarni, Pavan Turaga

We propose a framework called ReFInE to directly obtain integral image estimates from a very small number of spatially multiplexed measurements of the scene without iterative reconstruction of any auxiliary image, and demonstrate their practical utility in visual object tracking.

Visual Object Tracking

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

Reconstruction-free action inference from compressive imagers

no code implementations18 Jan 2015 Kuldeep Kulkarni, Pavan Turaga

In this paper, we propose reconstruction-free methods for action recognition from compressive cameras at high compression ratios of 100 and above.

Action Recognition Compressive Sensing

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

Manifold Precis: An Annealing Technique for Diverse Sampling of Manifolds

no code implementations NeurIPS 2011 Nitesh Shroff, Pavan Turaga, Rama Chellappa

In this paper, we consider the 'Precis' problem of sampling K representative yet diverse data points from a large dataset.

Document Summarization

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