Search Results for author: Sathya N. Ravi

Found 27 papers, 13 papers with code

Accelerated Neural Network Training with Rooted Logistic Objectives

no code implementations5 Oct 2023 Zhu Wang, Praveen Raj Veluswami, Harsh Mishra, Sathya N. Ravi

Furthermore, we illustrate applications of our novel rooted loss function in generative modeling based downstream applications, such as finetuning StyleGAN model with the rooted loss.

Binary Classification Data Augmentation

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization

1 code implementation12 Feb 2023 Hamidreza Almasi, Harsh Mishra, Balajee Vamanan, Sathya N. Ravi

Therefore, to scale computation and data, these models are inevitably trained in a distributed manner in clusters of nodes, and their updates are aggregated before being applied to the model.

Data Augmentation

Using Intermediate Forward Iterates for Intermediate Generator Optimization

no code implementations5 Feb 2023 Harsh Mishra, Jurijs Nazarovs, Manmohan Dogra, Sathya N. Ravi

In score-based models, a generative task is formulated using a parametric model (such as a neural network) to directly learn the gradient of such high dimensional distributions, instead of the density functions themselves, as is done traditionally.

Denoising

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

1 code implementation CVPR 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

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.

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.

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.

Rolling Shutter Correction

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.

Attribute Decision Making +1

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.

Quantization

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 Relationship Detection +1

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

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.

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

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.

Denoising

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.

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).

Quantization Retrieval

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.

Image Segmentation Semantic Segmentation +1

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.

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.

Denoising

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