Open AccessPosted Content
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Reads0
Chats0
TLDR
This work proposes a small DNN architecture called SqueezeNet, which achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and is able to compress to less than 0.5MB (510x smaller than AlexNet).Abstract:
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet).
The SqueezeNet architecture is available for download here: this https URLread more
Citations
More filters
Journal ArticleDOI
Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks.
Ali Abbasian Ardakani,Alireza Rajabzadeh Kanafi,U. Rajendra Acharya,Nazanin Khadem,Afshin Mohammadi +4 more
TL;DR: ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.
Journal ArticleDOI
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
TL;DR: By consolidating information scattered across the communication, networking, and DL areas, this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of edge intelligence and intelligent edge, i.e., Edge DL.
Proceedings ArticleDOI
Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
TL;DR: A novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor is proposed, which is very efficient in terms of both memory and computation.
Book ChapterDOI
Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
TL;DR: Zhang et al. as discussed by the authors proposed an accurate and lightweight deep network for image super-resolution, which implements a cascading mechanism upon a residual network and achieves state-of-the-art performance.
Journal ArticleDOI
Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study.
Jakob Nikolas Kather,Johannes Krisam,Pornpimol Charoentong,Pornpimol Charoentong,Tom Luedde,Esther Herpel,Cleo Aron Weis,Timo Gaiser,Alexander Marx,Nektarios A. Valous,Nektarios A. Valous,Dyke Ferber,Dyke Ferber,Lina Jansen,Constantino Carlos Reyes-Aldasoro,Inka Zörnig,Inka Zörnig,Dirk Jäger,Dirk Jäger,Hermann Brenner,Jenny Chang-Claude,Michael Hoffmeister,Niels Halama +22 more
TL;DR: It is shown that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images and was an independent prognostic factor for overall survival in a multivariable Cox proportional hazard model.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.