no code implementations • 11 Oct 2023 • Ravit Sharma, Wojciech Romaszkan, Feiqian Zhu, Puneet Gupta, Ankur Mehta
We perform this hardware/software co-design from the cost, latency, and user-experience perspective, and develop a set of guidelines for optimal system design and model deployment for the most cost-constrained platforms.
no code implementations • 8 Apr 2023 • Tianmu Li, Shurui Li, Puneet Gupta
Approximate computing methods have shown great potential for deep learning.
no code implementations • 10 Nov 2022 • Shurui Li, Hangbo Yang, Chee Wei Wong, Volker J. Sorger, Puneet Gupta
The last few years have seen a lot of work to address the challenge of low-latency and high-throughput convolutional neural network inference.
no code implementations • 25 Jan 2022 • Shurui Li, Puneet Gupta
Applications of neural networks on edge systems have proliferated in recent years but the ever-increasing model size makes neural networks not able to deploy on resource-constrained microcontrollers efficiently.
no code implementations • 23 Dec 2021 • Zibo Hu, Shurui Li, Russell L. T. Schwartz, Maria Solyanik-Gorgone, Mario Miscuglio, Puneet Gupta, Volker J. Sorger
Convolutional neural networks are paramount in image and signal processing including the relevant classification and training tasks alike and constitute for the majority of machine learning compute demand today.
1 code implementation • journal 2021 • Lokendra Birla, Puneet Gupta
To achieve the best possible performance, our novel method, 𝑃𝐴𝑇𝑅𝑂𝑁 that is resPiration bAsed feaTuRes fOr 3D face mask aNti-spoofing is based on: i)different characteristics as that of rPPG methods; ii) appropriate selection of facial regions; iii) relevant feature selection, and iv) compact feature representation.
no code implementations • 1 Mar 2021 • Shurui Li, Wojciech Romaszkan, Alexander Graening, Puneet Gupta
Quantization is spearheading the increase in performance and efficiency of neural network computing systems making headway into commodity hardware.
no code implementations • 10 May 2020 • Puneet Gupta, Brojeshwar Bhowmick, Arpan Pal
We alleviate these issues by proposing a novel face video based HR monitoring method MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking.
no code implementations • ICCV 2019 • Puneet Gupta, Esa Rahtu
This paper presents a novel approach for protecting deep neural networks from adversarial attacks, i. e., methods that add well-crafted imperceptible modifications to the original inputs such that they are incorrectly classified with high confidence.
no code implementations • 30 Jul 2019 • Saptadeep Pal, Eiman Ebrahimi, Arslan Zulfiqar, Yaosheng Fu, Victor Zhang, Szymon Migacz, David Nellans, Puneet Gupta
This work explores hybrid parallelization, where each data parallel worker is comprised of more than one device, across which the model dataflow graph (DFG) is split using MP.