activity
20172021
most citedAdversarial Token Attacks on Vision Transformers

9 citations · 9 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV20219 cited

Adversarial Token Attacks on Vision Transformers

Ameya Joshi, Gauri Jagatap, Chinmay Hegde

Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families o…

stat.ML2021

Provable Compressed Sensing with Generative Priors via Langevin Dynamics

Thanh V. Nguyen, Gauri Jagatap, Chinmay Hegde

Deep generative models have emerged as a powerful class of priors for signals in various inverse problems such as compressed sensing, phase retrieval and super-resolution. Here, we…

cs.LG2020

Adversarially Robust Learning via Entropic Regularization

Gauri Jagatap, Ameya Joshi, Animesh Basak Chowdhury +2

In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additi…

cs.CV2019

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors

Gauri Jagatap, Chinmay Hegde

Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafte…

cs.LG2018

Learning ReLU Networks via Alternating Minimization

Gauri Jagatap, Chinmay Hegde

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimat…

stat.ML2017

Sample-Efficient Algorithms for Recovering Structured Signals from Magnitude-Only Measurements

Gauri Jagatap, Chinmay Hegde

We consider the problem of recovering a signal , from magnitude-only measurements for $i…