SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis

2017-11-20 · Mohammad Javad Shafiee, Francis Li, Brendan Chwyl, Alexander Wong

While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread deployment on edge devices such as mobile and other consumer devices is high computational and memory requirements. Recently, there has been greater exploration into small deep neural network architectures that are more suitable for edge devices, with one of the most popular architectures being SqueezeNet, with an incredibly small model size of 4.8MB. Taking further advantage of the notion that many applications of machine learning on edge devices are often characterized by a low number of target classes, this study explores the utility of combining architectural modifications and an evolutionary synthesis strategy for synthesizing even smaller deep neural architectures based on the more recent SqueezeNet v1.1 macroarchitecture for applications with fewer target classes. In particular, architectural modifications are first made to SqueezeNet v1.1 to accommodate for a 10-class ImageNet-10 dataset, and then an evolutionary synthesis strategy is leveraged to synthesize more efficient deep neural networks based on this modified macroarchitecture. The resulting SquishedNets possess model sizes ranging from 2.4MB to 0.95MB (~5.17X smaller than SqueezeNet v1.1, or 253X smaller than AlexNet). Furthermore, the SquishedNets are still able to achieve accuracies ranging from 81.2% to 77%, and able to process at speeds of 156 images/sec to as much as 256 images/sec on a Nvidia Jetson TX1 embedded chip. These preliminary results show that a combination of architectural modifications and an evolutionary synthesis strategy can be a useful tool for producing very small deep neural network architectures that are well-suited for edge device scenarios.

📄 PDF Abstract BibTeX arXiv:1711.07459

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Residual Connection 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Average Pooling 설명 없음

Fire Module 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

A Scalable Multilabel Classification to Deploy Deep Learning Architectures For Edge Devices

2019-11-05 · Tolulope A. Odetola, Ogheneuriri Oderhohwo, Syed Rafay Hasan

Convolution Neural Networks (CNN) have performed well in many applications such as object detection, pattern recognition, video surveillance and so on. CNN carryout feature extraction on labelled data to perform classifi…

Classification General Classification Multi-Label Classification MUlTI-LABEL-ClASSIFICATION+2

Fire SSD: Wide Fire Modules based Single Shot Detector on Edge Device

2018-06-14 · Hengfui Liau, Nimmagadda Yamini, YengLiong Wong

With the emergence of edge computing, there is an increasing need for running convolutional neural network based object detection on small form factor edge computing devices with limited compute and thermal budget for ap…

CPU Edge-computing GPU Object+2

UltraLightSqueezeNet: A Deep Learning Architecture for Malaria Classification with up to 54x fewer trainable parameters for resource constrained devices

2025-01-24 · Suresh Babu Nettur, Shanthi Karpurapu, Unnati Nettur, Likhit Sagar Gajja 외

Lightweight deep learning approaches for malaria detection have gained attention for their potential to enhance diagnostics in resource constrained environments. For our study, we selected SqueezeNet1.1 as it is one of t…

Computational Efficiency

From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

2026-02-10 · Radib Bin Kabir, Tawsif Tashwar Dipto, Mehedi Ahamed, Sabbir Ahmed 외 arxiv

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale…

Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection

2025-06-14 · Akwasi Asare, Dennis Agyemanh Nana Gookyi, Derrick Boateng, Fortunatus Aabangbio Wulnye

Diabetic Retinopathy (DR), a leading cause of vision impairment in individuals with diabetes, affects approximately 34.6% of diabetes patients globally, with the number of cases projected to reach 242 million by 2045. Tr…

Diabetic Retinopathy Detection GPU