Search Results for author: Vishnu Naresh Boddeti

Found 41 papers, 20 papers with code

AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE

no code implementations12 Oct 2023 Wei Ao, Vishnu Naresh Boddeti

Lastly, AutoFHE accelerates inference and improves accuracy by $103\times$ and 3. 46%, respectively, compared to CNNs under TFHE.

Spurious Correlations and Where to Find Them

no code implementations21 Aug 2023 Gautam Sreekumar, Vishnu Naresh Boddeti

Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning.

Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services

no code implementations12 Aug 2023 Zhichao Lu, Chuntao Ding, Shangguang Wang, Ran Cheng, Felix Juefei-Xu, Vishnu Naresh Boddeti

However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models.

Semantic Segmentation

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives

no code implementations CVPR 2023 Chuntao Ding, Zhichao Lu, Shangguang Wang, Ran Cheng, Vishnu Naresh Boddeti

Our key idea is to employ non-learnable primitives to extract a diverse set of task-agnostic features and recombine them into a shared branch common to all tasks and explicit task-specific branches reserved for each task.

Multi-Task Learning

On the Biometric Capacity of Generative Face Models

no code implementations3 Aug 2023 Vishnu Naresh Boddeti, Gautam Sreekumar, Arun Ross

Our capacity estimates indicate that (a) under ArcFace representation at a false acceptance rate (FAR) of 0. 1%, StyleGAN3 and DCFace have a capacity upper bound of $1. 43\times10^6$ and $1. 190\times10^4$, respectively; (b) the capacity reduces drastically as we lower the desired FAR with an estimate of $1. 796\times10^4$ and $562$ at FAR of 1% and 10%, respectively, for StyleGAN3; (c) there is no discernible disparity in the capacity w. r. t gender; and (d) for some generative models, there is an appreciable disparity in the capacity w. r. t age.

Face Model

Discovering Adaptable Symbolic Algorithms from Scratch

no code implementations31 Jul 2023 Stephen Kelly, Daniel S. Park, Xingyou Song, Mitchell McIntire, Pranav Nashikkar, Ritam Guha, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti, Jie Tan, Esteban Real

We evolve modular policies that tune their model parameters and alter their inference algorithm on-the-fly to adapt to sudden environmental changes.


TFormer: A Transmission-Friendly ViT Model for IoT Devices

no code implementations15 Feb 2023 Zhichao Lu, Chuntao Ding, Felix Juefei-Xu, Vishnu Naresh Boddeti, Shangguang Wang, Yun Yang

The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN).

Image Classification object-detection +2

Revisiting Residual Networks for Adversarial Robustness

1 code implementation CVPR 2023 Shihua Huang, Zhichao Lu, Kalyanmoy Deb, Vishnu Naresh Boddeti

Then we design a robust residual block, dubbed RobustResBlock, and a compound scaling rule, dubbed RobustScaling, to distribute depth and width at the desired FLOP count.

Adversarial Robustness

ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding

no code implementations CVPR 2023 Lan Wang, Gaurav Mittal, Sandra Sajeev, Ye Yu, Matthew Hall, Vishnu Naresh Boddeti, Mei Chen

We present ProTeGe as the first method to perform VTG-based untrimmed pretraining to bridge the gap between trimmed pretrained backbones and downstream VTG tasks.

text similarity

Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective

1 code implementation21 Dec 2022 Shihua Huang, Zhichao Lu, Kalyanmoy Deb, Vishnu Naresh Boddeti

In contrast, little attention was devoted to analyzing the role of architectural elements (such as topology, depth, and width) on adversarial robustness.

Adversarial Robustness

Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components

no code implementations19 Dec 2022 Hamed Bolandi, Gautam Sreekumar, Xuyang Li, Nizar Lajnef, Vishnu Naresh Boddeti

Therefore, to reduce computational cost while preserving accuracy, a deep learning model, Neuro-DynaStress, is proposed to predict the entire sequence of stress distribution based on finite element simulations using a partial differential equation (PDE) solver.

Physics Informed Neural Network for Dynamic Stress Prediction

no code implementations28 Nov 2022 Hamed Bolandi, Gautam Sreekumar, Xuyang Li, Nizar Lajnef, Vishnu Naresh Boddeti

Therefore, to reduce computational cost while maintaining accuracy, a Physics Informed Neural Network (PINN), PINN-Stress model, is proposed to predict the entire sequence of stress distribution based on Finite Element simulations using a partial differential equation (PDE) solver.

NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems

1 code implementation26 Aug 2022 Xuyang Li, Hamed Bolandi, Talal Salem, Nizar Lajnef, Vishnu Naresh Boddeti

Structural monitoring for complex built environments often suffers from mismatch between design, laboratory testing, and actual built parameters.

HEFT: Homomorphically Encrypted Fusion of Biometric Templates

1 code implementation15 Aug 2022 Luke Sperling, Nalini Ratha, Arun Ross, Vishnu Naresh Boddeti

This paper proposes a non-interactive end-to-end solution for secure fusion and matching of biometric templates using fully homomorphic encryption (FHE).

Dimensionality Reduction

Do learned representations respect causal relationships?

1 code implementation CVPR 2022 Lan Wang, Vishnu Naresh Boddeti

Second, we apply NCINet to identify the causal relations between image representations of different pairs of attributes with known and unknown causal relations between the labels.

Causal Discovery Representation Learning

Generating Diverse 3D Reconstructions from a Single Occluded Face Image

1 code implementation CVPR 2022 Rahul Dey, Vishnu Naresh Boddeti

Furthermore, while a plurality of 3D reconstructions is plausible in the occluded regions, existing approaches are limited to generating only a single solution.

3D Reconstruction

Adversarial Representation Learning With Closed-Form Solvers

1 code implementation12 Sep 2021 Bashir Sadeghi, Lan Wang, Vishnu Naresh Boddeti

Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time.

Representation Learning

Spatially-Adaptive Image Restoration using Distortion-Guided Networks

no code implementations ICCV 2021 Kuldeep Purohit, Maitreya Suin, A. N. Rajagopalan, Vishnu Naresh Boddeti

However, we hypothesize that such spatially rigid processing is suboptimal for simultaneously restoring the degraded pixels as well as reconstructing the clean regions of the image.

Image Restoration

MUXConv: Information Multiplexing in Convolutional Neural Networks

1 code implementation CVPR 2020 Zhichao Lu, Kalyanmoy Deb, Vishnu Naresh Boddeti

To overcome this limitation, we present MUXConv, a layer that is designed to increase the flow of information by progressively multiplexing channel and spatial information in the network, while mitigating computational complexity.

Image Classification Neural Architecture Search +5

HERS: Homomorphically Encrypted Representation Search

1 code implementation27 Mar 2020 Joshua J. Engelsma, Anil K. Jain, Vishnu Naresh Boddeti

We present a method to search for a probe (or query) image representation against a large gallery in the encrypted domain.

Image Retrieval

Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification

1 code implementation3 Dec 2019 Zhichao Lu, Ian Whalen, Yashesh Dhebar, Kalyanmoy Deb, Erik Goodman, Wolfgang Banzhaf, Vishnu Naresh Boddeti

While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches.

Classification General Classification +3

On the Global Optima of Kernelized Adversarial Representation Learning

1 code implementation ICCV 2019 Bashir Sadeghi, Runyi Yu, Vishnu Naresh Boddeti

Numerical experiments on UCI, Extended Yale B and CIFAR-100 datasets indicate that, (a) practically, our solution is ideal for "imparting" provable invariance to any biased pre-trained data representation, and (b) empirically, the trade-off between utility and invariance provided by our solution is comparable to iterative minimax optimization of existing deep neural network based approaches.

Representation Learning

Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach

1 code implementation CVPR 2019 Proteek Chandan Roy, Vishnu Naresh Boddeti

Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images.

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

1 code implementation19 Dec 2018 Rahul Dey, Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

We present a new stage-wise learning paradigm for training generative adversarial networks (GANs).

Face Generation

Perturbative Neural Networks

3 code implementations CVPR 2018 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

Convolutional neural networks are witnessing wide adoption in computer vision systems with numerous applications across a range of visual recognition tasks.

Secure Face Matching Using Fully Homomorphic Encryption

1 code implementation1 May 2018 Vishnu Naresh Boddeti

In this paper, we explore the practicality of using a fully homomorphic encryption based framework to secure a database of face templates.

Dimensionality Reduction Face Recognition +2

On the Intrinsic Dimensionality of Image Representations

2 code implementations CVPR 2019 Sixue Gong, Vishnu Naresh Boddeti, Anil K. Jain

This paper addresses the following questions pertaining to the intrinsic dimensionality of any given image representation: (i) estimate its intrinsic dimensionality, (ii) develop a deep neural network based non-linear mapping, dubbed DeepMDS, that transforms the ambient representation to the minimal intrinsic space, and (iii) validate the veracity of the mapping through image matching in the intrinsic space.

Efficient K-Shot Learning with Regularized Deep Networks

no code implementations6 Oct 2017 Donghyun Yoo, Haoqi Fan, Vishnu Naresh Boddeti, Kris M. Kitani

To efficiently search for optimal groupings conditioned on the input data, we propose a reinforcement learning search strategy using recurrent networks to learn the optimal group assignments for each network layer.

On the Capacity of Face Representation

no code implementations29 Sep 2017 Sixue Gong, Vishnu Naresh Boddeti, Anil K. Jain

Numerical experiments on unconstrained faces (IJB-C) provides a capacity upper bound of $2. 7\times10^4$ for FaceNet and $8. 4\times10^4$ for SphereFace representation at a false acceptance rate (FAR) of 1%.

Face Recognition

Face Alignment Robust to Pose, Expressions and Occlusions

no code implementations19 Jul 2017 Vishnu Naresh Boddeti, Myung-Cheol Roh, Jongju Shin, Takaharu Oguri, Takeo Kanade

To account for partial occlusions we introduce, Robust Constrained Local Models, that comprises of a deformable shape and local landmark appearance model and reasons over binary occlusion labels.

Face Alignment Test

Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking

1 code implementation17 Apr 2017 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

A recent advance called the WGAN based on Wasserstein distance can improve on the KL and JS-divergence based GANs, and alleviate the gradient vanishing, instability, and mode collapse issues that are common in the GAN training.

Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator

no code implementations15 Dec 2016 Namhoon Lee, Xinshuo Weng, Vishnu Naresh Boddeti, Yu Zhang, Fares Beainy, Kris Kitani, Takeo Kanade

We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.

Human Detection Pose Estimation

Gesture-based Bootstrapping for Egocentric Hand Segmentation

no code implementations9 Dec 2016 Yubo Zhang, Vishnu Naresh Boddeti, Kris M. Kitani

Concretely, our approach uses two convolutional neural networks: (1) a gesture network that uses pre-defined motion information to detect the hand region; and (2) an appearance network that learns a person specific model of the hand region based on the output of the gesture network.

Hand Segmentation

Local Binary Convolutional Neural Networks

7 code implementations CVPR 2017 Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN).

Learning Scene-Specific Pedestrian Detectors Without Real Data

no code implementations CVPR 2015 Hironori Hattori, Vishnu Naresh Boddeti, Kris M. Kitani, Takeo Kanade

Our results also yield a surprising result, that our method using purely synthetic data is able to outperform models trained on real scene-specific data when data is limited.

Pedestrian Detection

Zero-Aliasing Correlation Filters for Object Recognition

no code implementations10 Nov 2014 Joseph A. Fernandez, Vishnu Naresh Boddeti, Andres Rodriguez, B. V. K. Vijaya Kumar

However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain.

Object Localization Object Recognition

Maximum Margin Vector Correlation Filter

no code implementations24 Apr 2014 Vishnu Naresh Boddeti, B. V. K. Vijaya Kumar

Correlation Filters (CFs) are a class of classifiers which are designed for accurate pattern localization.

object-detection Object Detection

Correlation Filters for Object Alignment

no code implementations CVPR 2013 Vishnu Naresh Boddeti, Takeo Kanade, B. V. K. Vijaya Kumar

A typical object alignment system consists of a landmark appearance model which is used to obtain an initial shape and a shape model which refines this initial shape by correcting the initialization errors.

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