Search Results for author: Vikas Singh

Found 71 papers, 22 papers with code

Deep Unlearning via Randomized Conditionally Independent Hessians

1 code implementation15 Apr 2022 Ronak Mehta, Sourav Pal, Vikas Singh, Sathya N. Ravi

For models which require no training (k-NN), simply deleting the closest original sample can be effective.

Face Recognition Person Re-Identification

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

1 code implementation29 Mar 2022 Vishnu Suresh Lokhande, Rudrasis Chakraborty, Sathya N. Ravi, Vikas Singh

Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e. g., between risk factors and disease outcomes) that may otherwise be too weak to detect.

Causal Inference Domain Adaptation +1

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks

no code implementations19 Feb 2022 Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh

This is directly related to the structure of the computation graph, which can grow linearly as a function of the number of MC samples needed.

Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data

no code implementations18 Feb 2022 Jurijs Nazarovs, Rudrasis Chakraborty, Songwong Tasneeyapant, Sathya N. Ravi, Vikas Singh

Panel data involving longitudinal measurements of the same set of participants taken over multiple time points is common in studies to understand childhood development and disease modeling.

Forward Operator Estimation in Generative Models with Kernel Transfer Operators

no code implementations1 Dec 2021 Zhichun Huang, Rudrasis Chakraborty, Vikas Singh

Generative models which use explicit density modeling (e. g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e. g. Gaussian, to the unknown input distribution.

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

1 code implementation18 Nov 2021 Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi, Shailesh Acharya, Glenn Fung, Vikas Singh

In this paper, we show that a Bernoulli sampling attention mechanism based on Locality Sensitive Hashing (LSH), decreases the quadratic complexity of such models to linear.

Distribution Matching in Deep Generative Models with Kernel Transfer Operators

no code implementations29 Sep 2021 Zhichun Huang, Rudrasis Chakraborty, Vikas Singh

Generative models which use explicit density modeling (e. g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e. g. Gaussian, to the unknown input distribution.

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

1 code implementation ICCV 2021 Zihang Meng, Vikas Singh, Sathya N. Ravi

We study how stochastic differential equation (SDE) based ideas can inspire new modifications to existing algorithms for a set of problems in computer vision.

Data Augmentation Few-Shot Image Classification

An Online Riemannian PCA for Stochastic Canonical Correlation Analysis

no code implementations NeurIPS 2021 Zihang Meng, Rudrasis Chakraborty, Vikas Singh

We present an efficient stochastic algorithm (RSG+) for canonical correlation analysis (CCA) using a reparametrization of the projection matrices.

Connecting What to Say With Where to Look by Modeling Human Attention Traces

1 code implementation CVPR 2021 Zihang Meng, Licheng Yu, Ning Zhang, Tamara Berg, Babak Damavandi, Vikas Singh, Amy Bearman

Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded.

Image Captioning Visual Grounding

Simpler Certified Radius Maximization by Propagating Covariances

1 code implementation CVPR 2021 Xingjian Zhen, Rudrasis Chakraborty, Vikas Singh

One strategy for adversarially training a robust model is to maximize its certified radius -- the neighborhood around a given training sample for which the model's prediction remains unchanged.

Learning Invariant Representations using Inverse Contrastive Loss

1 code implementation16 Feb 2021 Aditya Kumar Akash, Vishnu Suresh Lokhande, Sathya N. Ravi, Vikas Singh

Learning invariant representations is a critical first step in a number of machine learning tasks.

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

no code implementations NeurIPS 2021 Zihang Meng, Lopamudra Mukherjee, Vikas Singh, Sathya N. Ravi

We propose a framework which makes it feasible to directly train deep neural networks with respect to popular families of task-specific non-decomposable per- formance measures such as AUC, multi-class AUC, F -measure and others, as well as models such as non-negative matrix factorization.

Stochastic Canonical Correlation Analysis: A Riemannian Approach

no code implementations1 Jan 2021 Zihang Meng, Rudrasis Chakraborty, Vikas Singh

We present an efficient stochastic algorithm (RSG+) for canonical correlation analysis (CCA) derived via a differential geometric perspective of the underlying optimization task.

Can Kernel Transfer Operators Help Flow based Generative Models?

no code implementations1 Jan 2021 Zhichun Huang, Rudrasis Chakraborty, Xingjian Zhen, Vikas Singh

Flow-based generative models refer to deep generative models with tractable likelihoods, and offer several attractive properties including efficient density estimation and sampling.

Density Estimation

Flow-based Generative Models for Learning Manifold to Manifold Mappings

1 code implementation18 Dec 2020 Xingjian Zhen, Rudrasis Chakraborty, Liu Yang, Vikas Singh

Partly due to this gap, there are also no modality transfer/translation models for manifold-valued data whereas numerous such methods based on generative models are available for natural images.

Simplicial 2-Complex Convolutional Neural Networks

no code implementations NeurIPS Workshop TDA_and_Beyond 2020 Eric Bunch, Qian You, Glenn Fung, Vikas Singh

Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph.

A Bayesian Approach with Type-2 Student-tMembership Function for T-S Model Identification

no code implementations2 Sep 2020 Vikas Singh, Homanga Bharadhwaj, Nishchal K. Verma

Clustering techniques have been proved highly suc-cessful for Takagi-Sugeno (T-S) fuzzy model identification.

Online Graph Completion: Multivariate Signal Recovery in Computer Vision

no code implementations CVPR 2017 Won Hwa Kim, Mona Jalal, Seongjae Hwang, Sterling C. Johnson, Vikas Singh

The adoption of "human-in-the-loop" paradigms in computer vision and machine learning is leading to various applications where the actual data acquisition (e. g., human supervision) and the underlying inference algorithms are closely interwined.

Active Learning Collaborative Filtering +1

Improved Adaptive Type-2 Fuzzy Filter with Exclusively Two Fuzzy Membership Function for Filtering Salt and Pepper Noise

no code implementations10 Aug 2020 Vikas Singh, Pooja Agrawal, Teena Sharma, Nishchal K. Verma

The performance of the proposed filter is compared with the various state-of-the-art methods in terms of peak signal-to-noise ratio and computation time.

Image Denoising

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

4 code implementations CVPR 2021 Yunyang Xiong, Hanxiao Liu, Suyog Gupta, Berkin Akin, Gabriel Bender, Yongzhe Wang, Pieter-Jan Kindermans, Mingxing Tan, Vikas Singh, Bo Chen

By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators.

Neural Architecture Search Object Detection

Physarum Powered Differentiable Linear Programming Layers and Applications

3 code implementations30 Apr 2020 Zihang Meng, Sathya N. Ravi, Vikas Singh

We describe our development and show the use of our solver in a video segmentation task and meta-learning for few-shot learning.

Few-Shot Learning Semantic Segmentation +3

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

1 code implementation ECCV 2020 Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh

We provide a detailed technical analysis and present experiments demonstrating that various fairness measures from the literature can be reliably imposed on a number of training tasks in vision in a manner that is interpretable.

Decision Making Fairness

Intelligent Condition Based Monitoring Techniques for Bearing Fault Diagnosis

no code implementations24 Dec 2019 Vikas Singh, Nishchal K. Verma

In recent years, intelligent condition-based monitor-ing of rotary machinery systems has become a major researchfocus of machine fault diagnosis.

Transfer Learning

An Entropy-based Variable Feature Weighted Fuzzy k-Means Algorithm for High Dimensional Data

no code implementations24 Dec 2019 Vikas Singh, Nishchal K. Verma

This paper presents a new fuzzy k-means algorithm for the clustering of high dimensional data in various subspaces.

Dilated Convolutional Neural Networks for Sequential Manifold-valued Data

1 code implementation ICCV 2019 Xingjian Zhen, Rudrasis Chakraborty, Nicholas Vogt, Barbara B. Bendlin, Vikas Singh

Efforts are underway to study ways via which the power of deep neural networks can be extended to non-standard data types such as structured data (e. g., graphs) or manifold-valued data (e. g., unit vectors or special matrices).

Fooling Computer Vision into Inferring the Wrong Body Mass Index

no code implementations16 May 2019 Owen Levin, Zihang Meng, Vikas Singh, Xiaojin Zhu

Recently it's been shown that neural networks can use images of human faces to accurately predict Body Mass Index (BMI), a widely used health indicator.

General Classification

Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?

1 code implementation ICCV 2019 Yunyang Xiong, Ronak Mehta, Vikas Singh

In the latter case, the optimization is often non-differentiable and also not very amenable to derivative-free optimization methods.

Neural Architecture Search

Conditional Recurrent Flow: Conditional Generation of Longitudinal Samples with Applications to Neuroimaging

no code implementations ICCV 2019 Seong Jae Hwang, Zirui Tao, Won Hwa Kim, Vikas Singh

Such models may work for cross-sectional studies, however, they are not suitable to generate data for longitudinal studies that focus on "progressive" behavior in a sequence of data.

Efficient Relative Attribute Learning using Graph Neural Networks

1 code implementation ECCV 2018 Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh

A sizable body of work on relative attributes provides compelling evidence that relating pairs of images along a continuum of strength pertaining to a visual attribute yields significant improvements in a wide variety of tasks in vision.

Building Bayesian Neural Networks with Blocks: On Structure, Interpretability and Uncertainty

no code implementations10 Jun 2018 Hao Henry Zhou, Yunyang Xiong, Vikas Singh

We provide simple schemes to build Bayesian Neural Networks (BNNs), block by block, inspired by a recent idea of computation skeletons.

Gaussian Processes Variational Inference

A Biresolution Spectral Framework for Product Quantization

no code implementations CVPR 2018 Lopamudra Mukherjee, Sathya N. Ravi, Jiming Peng, Vikas Singh

In this paper, we study the quantization problem in the setting where subspaces are orthogonal and show that this problem is intricately related to a specific type of spectral decomposition of the data.


Tensorize, Factorize and Regularize: Robust Visual Relationship Learning

no code implementations CVPR 2018 Seong Jae Hwang, Sathya N. Ravi, Zirui Tao, Hyunwoo J. Kim, Maxwell D. Collins, Vikas Singh

Visual relationships provide higher-level information of objects and their relations in an image – this enables a semantic understanding of the scene and helps downstream applications.

Relational Reasoning Visual Relationship Detection

Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families

no code implementations19 Apr 2018 Seong Jae Hwang, Ronak Mehta, Hyunwoo J. Kim, Vikas Singh

There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make.

Robust Blind Deconvolution via Mirror Descent

4 code implementations21 Mar 2018 Sathya N. Ravi, Ronak Mehta, Vikas Singh

We revisit the Blind Deconvolution problem with a focus on understanding its robustness and convergence properties.

Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision

1 code implementation17 Mar 2018 Sathya N. Ravi, Tuan Dinh, Vishnu Sai Rao Lokhande, Vikas Singh

We provide convergence guarantees and show a suite of immediate benefits that are possible -- from training ResNets with fewer layers but better accuracy simply by substituting in our version of CG to faster training of GANs with 50% fewer epochs in image inpainting applications to provably better generalization guarantees using efficiently implementable forms of recently proposed regularizers.

Image Inpainting

Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective

no code implementations20 Nov 2017 Ronak Mehta, Hyunwoo J. Kim, Shulei Wang, Sterling C. Johnson, Ming Yuan, Vikas Singh

Recent results in coupled or temporal graphical models offer schemes for estimating the relationship structure between features when the data come from related (but distinct) longitudinal sources.

A Geometric Framework for Statistical Analysis of Trajectories With Distinct Temporal Spans

no code implementations ICCV 2017 Rudrasis Chakraborty, Vikas Singh, Nagesh Adluru, Baba C. Vemuri

Finally, by using existing algorithms for recursive Frechet mean and exact principal geodesic analysis on the hypersphere, we present several experiments on synthetic and real (vision and medical) data sets showing how group testing on such diversely sampled longitudinal data is possible by analyzing the reconstructed data in the subspace spanned by the first few PGs.

A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees

no code implementations22 Aug 2017 Sathya N. Ravi, Maxwell D. Collins, Vikas Singh

We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective.

Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging

no code implementations CVPR 2017 Hyunwoo J. Kim, Nagesh Adluru, Heemanshu Suri, Baba C. Vemuri, Sterling C. Johnson, Vikas Singh

Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging.

Activity Recognition

Filter Flow Made Practical: Massively Parallel and Lock-Free

1 code implementation CVPR 2017 Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh

This paper is inspired by a relatively recent work of Seitz and Baker which introduced the so-called Filter Flow model.

Optical Flow Estimation

Accelerating Permutation Testing in Voxel-wise Analysis through Subspace Tracking: A new plugin for SnPM

no code implementations4 Mar 2017 Felipe Gutierrez-Barragan, Vamsi K. Ithapu, Chris Hinrichs, Camille Maumet, Sterling C. Johnson, Thomas E. Nichols, Vikas Singh, the ADNI

We find that RapidPT achieves its best runtime performance on medium sized datasets ($50 \leq n \leq 200$), with speedups of 1. 5x - 38x (vs. SnPM13) and 20x-1000x (vs. NaivePT).

Low-Rank Matrix Completion

On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation

no code implementations28 Feb 2017 Vamsi K. Ithapu, Sathya N. Ravi, Vikas Singh

We seek to analyze whether network architecture and input data statistics may guide the choices of learning parameters and vice versa.


Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP)

no code implementations CVPR 2016 Won Hwa Kim, Hyunwoo J. Kim, Nagesh Adluru, Vikas Singh

A major goal of imaging studies such as the (ongoing) Human Connectome Project (HCP) is to characterize the structural network map of the human brain and identify its associations with covariates such as genotype, risk factors, and so on that correspond to an individual.

Model Selection

Coupled Harmonic Bases for Longitudinal Characterization of Brain Networks

no code implementations CVPR 2016 Seong Jae Hwang, Nagesh Adluru, Maxwell D. Collins, Sathya N. Ravi, Barbara B. Bendlin, Sterling C. Johnson, Vikas Singh

There is a great deal of interest in using large scale brain imaging studies to understand how brain connectivity evolves over time for an individual and how it varies over different levels/quantiles of cognitive function.

Interpolation on the Manifold of K Component GMMs

no code implementations ICCV 2015 Hyunwoo J. Kim, Nagesh Adluru, Monami Banerjee, Baba C. Vemuri, Vikas Singh

Probability density functions (PDFs) are fundamental "objects" in mathematics with numerous applications in computer vision, machine learning and medical imaging.

On Statistical Analysis of Neuroimages With Imperfect Registration

no code implementations ICCV 2015 Won Hwa Kim, Sathya N. Ravi, Sterling C. Johnson, Ozioma C. Okonkwo, Vikas Singh

A variety of studies in neuroscience/neuroimaging seek to perform statistical inference on the acquired brain image scans for diagnosis as well as understanding the pathological manifestation of diseases.

A Projection Free Method for Generalized Eigenvalue Problem With a Nonsmooth Regularizer

no code implementations ICCV 2015 Seong Jae Hwang, Maxwell D. Collins, Sathya N. Ravi, Vamsi K. Ithapu, Nagesh Adluru, Sterling C. Johnson, Vikas Singh

Eigenvalue problems are ubiquitous in computer vision, covering a very broad spectrum of applications ranging from estimation problems in multi-view geometry to image segmentation.

Semantic Segmentation Stochastic Optimization

An NMF Perspective on Binary Hashing

no code implementations ICCV 2015 Lopamudra Mukherjee, Sathya N. Ravi, Vamsi K. Ithapu, Tyler Holmes, Vikas Singh

In this paper, we first derive an Augmented Lagrangian approach to optimize the standard binary Hashing objective (i. e., maintain fidelity with a given distance matrix).


On the interplay of network structure and gradient convergence in deep learning

no code implementations17 Nov 2015 Vamsi K. Ithapu, Sathya N. Ravi, Vikas Singh

The regularization and output consistency behavior of dropout and layer-wise pretraining for learning deep networks have been fairly well studied.


Convergence rates for pretraining and dropout: Guiding learning parameters using network structure

no code implementations10 Jun 2015 Vamsi K. Ithapu, Sathya Ravi, Vikas Singh

Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency.


Statistical Inference Models for Image Datasets With Systematic Variations

no code implementations CVPR 2015 Won Hwa Kim, Barbara B. Bendlin, Moo. K. Chung, Sterling C. Johnson, Vikas Singh

Statistical analysis of longitudinal or cross sectionalbrain imaging data to identify effects of neurodegenerative diseases is a fundamental task in various studies in neuroscience.

Convergence of gradient based pre-training in Denoising autoencoders

no code implementations12 Feb 2015 Vamsi K. Ithapu, Sathya Ravi, Vikas Singh

The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network.

Denoising Unsupervised Pre-training

Speeding up Permutation Testing in Neuroimaging

no code implementations NeurIPS 2013 Chris Hinrichs, Vamsi K. Ithapu, Qinyuan Sun, Sterling C. Johnson, Vikas Singh

In this paper, we show that permutation testing in fact amounts to populating the columns of a very large matrix ${\bf P}$.

Matrix Completion Two-sample testing

Permutation Diffusion Maps (PDM) with Application to the Image Association Problem in Computer Vision

no code implementations NeurIPS 2014 Deepti Pachauri, Risi Kondor, Gautam Sargur, Vikas Singh

Consistently matching keypoints across images, and the related problem of finding clusters of nearby images, are critical components of various tasks in Computer Vision, including Structure from Motion (SfM).

Solving the multi-way matching problem by permutation synchronization

no code implementations NeurIPS 2013 Deepti Pachauri, Risi Kondor, Vikas Singh

The problem of matching not just two, but m different sets of objects to each other arises in a variety of contexts, including finding the correspondence between feature points across multiple images in computer vision.

Multi-resolution Shape Analysis via Non-Euclidean Wavelets: Applications to Mesh Segmentation and Surface Alignment Problems

no code implementations CVPR 2013 Won Hwa Kim, Moo. K. Chung, Vikas Singh

In this paper, we adapt recent results in harmonic analysis, to derive NonEuclidean Wavelets based algorithms for a range of shape analysis problems in vision and medical imaging.

Wavelet based multi-scale shape features on arbitrary surfaces for cortical thickness discrimination

no code implementations NeurIPS 2012 Won H. Kim, Deepti Pachauri, Charles Hatt, Moo. K. Chung, Sterling Johnson, Vikas Singh

In contrast to hypothesis tests on point-wise measurements, in this paper, we make the case for performing statistical analysis on multi-scale shape descriptors that characterize the local topological context of the signal around each surface vertex.

Two-sample testing

Q-MKL: Matrix-induced Regularization in Multi-Kernel Learning with Applications to Neuroimaging

no code implementations NeurIPS 2012 Chris Hinrichs, Vikas Singh, Jiming Peng, Sterling Johnson

Multiple Kernel Learning (MKL) generalizes SVMs to the setting where one simultaneously trains a linear classifier and chooses an optimal combination of given base kernels.

Epitome driven 3-D Diffusion Tensor image segmentation: on extracting specific structures

no code implementations NeurIPS 2010 Kamiya Motwani, Nagesh Adluru, Chris Hinrichs, Andrew Alexander, Vikas Singh

Now, given such a representation, the problem reduces to segmenting new brain image with additional constraints that enforce consistency between the segmented foreground and the pre-specified histogram over features.

Semantic Segmentation

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