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
Posted Content
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions.
Samuel Kriman,Stanislav Beliaev,Boris Ginsburg,Jocelyn Huang,Oleksii Kuchaiev,Vitaly Lavrukhin,Ryan Leary,Jason Li,Yang Zhang +8 more
TL;DR: In this paper, an end-to-end neural acoustic model for automatic speech recognition is proposed, which is composed of multiple blocks with residual connections between them, each block consists of one or more modules with 1D time-channel separable convolutional layers.
Proceedings ArticleDOI
Evaluation of a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery
Yona Falinie A. Gaus,Neelanjan Bhowmik,Samet Akcay,Paolo M. Guillen-Garcia,Jack W. Barker,Toby P. Breckon +5 more
TL;DR: A dual convolutional neural network architecture for automatic anomaly detection within complex security X-ray imagery and leveraging a range of established CNN object and fine-grained category classification approaches to formulate within object anomaly detection as a two-class problem (anomalous or benign).
Journal ArticleDOI
A lightweight deep learning algorithm for inspection of laser welding defects on safety vent of power battery
TL;DR: The proposed pre-trained SqueezeNet model with small model size and low computation complexity can help to conduct the laser welding quality inspection tasks that are usually performed by humans.
Posted Content
Deep Photovoltaic Nowcasting
TL;DR: This work proposes to learn the relationship between sky appearance and the future photovoltaic power output using deep learning, and compares three different architectures based on: a multi-layer perceptron (MLP), a convolutional neural network (CNN), and a long short term memory (LSTM) module.
Book ChapterDOI
Deep Expander Networks: Efficient Deep Networks from Graph Theory
TL;DR: X-Nets as mentioned in this paper use a well-studied class of graphs from theoretical computer science that satisfy these properties known as Expander graphs to model connections between filters in CNNs.
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.