Konda Reddy Mopuri

is this you? claim profile

0 followers
indian institute of science

Class Balancing GAN with a Classifier in the Loop

Generative Adversarial Networks (GANs) have swiftly evolved to imitate i...
06/17/2021 ∙ by Harsh Rangwani, et al. ∙ 10 ∙ share

read it
Data Impressions: Mining Deep Models to Extract Samples for Data-free Applications

Pretrained deep models hold their learnt knowledge in the form of the mo...
01/15/2021 ∙ by Gaurav Kumar Nayak, et al. ∙ 21 ∙ share

read it
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation

Knowledge Distillation is an effective method to transfer the learning a...
11/18/2020 ∙ by Gaurav Kumar Nayak, et al. ∙ 0 ∙ share

read it
Dataset Condensation with Gradient Matching

Efficient training of deep neural networks is an increasingly important ...
06/10/2020 ∙ by Bo Zhao, et al. ∙ 0 ∙ share

read it
Adversarial Fooling Beyond "Flipping the Label"

Recent advancements in CNNs have shown remarkable achievements in variou...
04/27/2020 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
iDLG: Improved Deep Leakage from Gradients

It is widely believed that sharing gradients will not leak private train...
01/08/2020 ∙ by Bo Zhao, et al. ∙ 0 ∙ share

read it
Zero-Shot Knowledge Distillation in Deep Networks

Knowledge distillation deals with the problem of training a smaller mode...
05/20/2019 ∙ by Gaurav Kumar Nayak, et al. ∙ 0 ∙ share

read it
Gray-box Adversarial Training

Adversarial samples are perturbed inputs crafted to mislead the machine ...
08/06/2018 ∙ by Vivek B. S., et al. ∙ 0 ∙ share

read it
Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions

Deep learning models are susceptible to input specific noise, called adv...
08/03/2018 ∙ by Konda Reddy Mopuri, et al. ∙ 4 ∙ share

read it
Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations

Machine learning models are susceptible to adversarial perturbations: sm...
01/24/2018 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
NAG: Network for Adversary Generation

Adversarial perturbations can pose a serious threat for deploying machin...
12/09/2017 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
CNN Fixations: An unraveling approach to visualize the discriminative image regions

Deep convolutional neural networks (CNN) have revolutionized various fie...
08/22/2017 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
Fast Feature Fool: A data independent approach to universal adversarial perturbations

State-of-the-art object recognition Convolutional Neural Networks (CNNs)...
07/18/2017 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
Deep image representations using caption generators

Deep learning exploits large volumes of labeled data to learn powerful m...
05/25/2017 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision

Traditional architectures for solving computer vision problems and the d...
01/25/2016 ∙ by Suraj Srinivas, et al. ∙ 0 ∙ share

read it
Object Level Deep Feature Pooling for Compact Image Representation

Convolutional Neural Network (CNN) features have been successfully emplo...
04/24/2015 ∙ by Konda Reddy Mopuri, et al. ∙ 0 ∙ share

read it

Konda Reddy Mopuri

Featured Co-authors

R. Venkatesh Babu

Bo Zhao

Hakan Bilen

Ravi Kiran Sarvadevabhatla

Anirban Chakraborty

Suraj Srinivas

Utkarsh Ojha

Aditya Ganeshan

Gaurav Kumar Nayak

Srinivas S S Kruthiventi

Utsav Garg

Class Balancing GAN with a Classifier in the Loop

Data Impressions: Mining Deep Models to Extract Samples for Data-free Applications

Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation

Dataset Condensation with Gradient Matching

Adversarial Fooling Beyond "Flipping the Label"

iDLG: Improved Deep Leakage from Gradients

Zero-Shot Knowledge Distillation in Deep Networks

Gray-box Adversarial Training

Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions

Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations

NAG: Network for Adversary Generation

CNN Fixations: An unraveling approach to visualize the discriminative image regions

Fast Feature Fool: A data independent approach to universal adversarial perturbations

Deep image representations using caption generators

A Taxonomy of Deep Convolutional Neural Nets for Computer Vision

Object Level Deep Feature Pooling for Compact Image Representation