activity
20182022
most citedPipeline Parallelism for Inference on Heterogeneous Edge Computing

12 citations · 45 across the 13 of their papers we have counts for

collaborators

18 papers

cs.DC2022

QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer Pipelines in Dynamic Edge Environments

Haonan Wang, Connor Imes, Souvik Kundu +3

Pipeline parallelism has achieved great success in deploying large-scale transformer models in cloud environments, but has received less attention in edge environments. Unlike in c…

eess.IV2022

P2M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking

Gourav Datta, Souvik Kundu, Zihan Yin +11

Today's high resolution, high frame rate cameras in autonomous vehicles generate a large volume of data that needs to be transferred and processed by a downstream processor or mach…

cs.CV2022

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness

Souvik Kundu, Sairam Sundaresan, Massoud Pedram +1

Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linea…

cs.LG2022

P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applications

Gourav Datta, Souvik Kundu, Zihan Yin +5

The demand to process vast amounts of data generated from state-of-the-art high resolution cameras has motivated novel energy-efficient on-device AI solutions. Visual data in such…

cs.DC202112 cited

Pipeline Parallelism for Inference on Heterogeneous Edge Computing

Yang Hu, Connor Imes, Xuanang Zhao +4

Deep neural networks with large model sizes achieve state-of-the-art results for tasks in computer vision (CV) and natural language processing (NLP). However, these large-scale mod…

cs.CV2021

HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise

Souvik Kundu, Massoud Pedram, Peter A. Beerel

Low-latency deep spiking neural networks (SNNs) have become a promising alternative to conventional artificial neural networks (ANNs) because of their potential for increased energ…