64 citations · 147 across the 44 of their papers we have counts for
5 papers · 1 filter
AttentionLite: Towards Efficient Self-Attention Models for Vision
Souvik Kundu, Sairam Sundaresan
We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has prim…
Attention-based Image Upsampling
Souvik Kundu, Hesham Mostafa, Sharath Nittur Sridhar +1
Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechani…
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs
Souvik Kundu, Mahdi Nazemi, Peter A. Beerel +1
This paper presents a dynamic network rewiring (DNR) method to generate pruned deep neural network (DNN) models that are robust against adversarial attacks yet maintain high accura…
Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks
Souvik Kundu, Mahdi Nazemi, Massoud Pedram +2
The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices.…
qBSA: Logic Design of a 32-bit Block-Skewed RSFQ Arithmetic Logic Unit
Souvik Kundu, Gourav datta, Peter A. Beerel +1
Single flux quantum (SFQ) circuits are an attractive beyond-CMOS technology because they promise two orders of magnitude lower power at clock frequencies exceeding 25 GHz.However,…