3 citations · 7 across the 11 of their papers we have counts for
11 papers
STResNet & STYOLO : A New Family of Compact Classification and Object Detection Models for MCUs
Sudhakar Sah, Ravish Kumar
Recent advancements in lightweight neural networks have significantly improved the efficiency of deploying deep learning models on edge hardware. However, most existing architectur…
CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition
Sudhakar Sah, Nikhil Chabbra, Matthieu Durnerin
Deep Convolutional Neural Networks (CNNs) are increasingly difficult to deploy on microcontrollers (MCUs) and lightweight NPUs (Neural Processing Units) due to their growing size a…
ActNAS : Generating Efficient YOLO Models using Activation NAS
Sudhakar Sah, Ravish Kumar, Darshan C. Ganji +1
Activation functions introduce non-linearity into Neural Networks, enabling them to learn complex patterns. Different activation functions vary in speed and accuracy, ranging from…
Token Pruning using a Lightweight Background Aware Vision Transformer
Sudhakar Sah, Ravish Kumar, Honnesh Rohmetra +1
High runtime memory and high latency puts significant constraint on Vision Transformer training and inference, especially on edge devices. Token pruning reduces the number of input…
MCUBench: A Benchmark of Tiny Object Detectors on MCUs
Sudhakar Sah, Darshan C. Ganji, Matteo Grimaldi +4
We introduce MCUBench, a benchmark featuring over 100 YOLO-based object detection models evaluated on the VOC dataset across seven different MCUs. This benchmark provides detailed…
QGen: On the Ability to Generalize in Quantization Aware Training
MohammadHossein AskariHemmat, Ahmadreza Jeddi, Reyhane Askari Hemmat +6
Quantization lowers memory usage, computational requirements, and latency by utilizing fewer bits to represent model weights and activations. In this work, we investigate the gener…
DeepliteRT: Computer Vision at the Edge
Saad Ashfaq, Alexander Hoffman, Saptarshi Mitra +3
The proliferation of edge devices has unlocked unprecedented opportunities for deep learning model deployment in computer vision applications. However, these complex models require…
YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems
Ivan Lazarevich, Matteo Grimaldi, Ravish Kumar +3
We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia…
DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables
Darshan C. Ganji, Saad Ashfaq, Ehsan Saboori +6
A lot of recent progress has been made in ultra low-bit quantization, promising significant improvements in latency, memory footprint and energy consumption on edge devices. Quanti…
Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime
Saad Ashfaq, MohammadHossein AskariHemmat, Sudhakar Sah +3
Deep Learning has been one of the most disruptive technological advancements in recent times. The high performance of deep learning models comes at the expense of high computationa…
QReg: On Regularization Effects of Quantization
MohammadHossein AskariHemmat, Reyhane Askari Hemmat, Alex Hoffman +6
In this paper we study the effects of quantization in DNN training. We hypothesize that weight quantization is a form of regularization and the amount of regularization is correlat…