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
Measuring and regularizing networks in function space
TL;DR: In this article, it is shown that the distance between functions in a Hilbert space can be computed in a way that minimally interferes with what has previously been learned, which can be applied directly to optimization.
Journal ArticleDOI
A lightweight neural network with strong robustness for bearing fault diagnosis
TL;DR: The experimental results show that the fault diagnosis of rolling bearing based on SIRCNN can effectively identify the type and severity of bearing fault under different noise environments, improve the diagnostic efficiency and reduce the performance requirements for the diagnostic equipment.
Journal ArticleDOI
A Deep Learning Iris Recognition Method Based on Capsule Network Architecture
TL;DR: Three state-of-the-art pretrained models, VGG16, InceptionV3, and ResNet50, are introduced and the structure detail of the network is adjusted, and a modified routing algorithm based on the dynamic routing between two capsule layers to make this technique adapt to iris recognition.
Journal ArticleDOI
Layer-Wise Training Convolutional Neural Networks With Smaller Filters for Human Activity Recognition Using Wearable Sensors
TL;DR: The experiment results indicate that the novel Lego CNN with local loss can greatly reduce memory and computation cost over CNN, while achieving higher accuracy, which is to say, the proposed model is smaller, faster and more accurate.
Posted Content
Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Cody Coleman,Daniel Kang,Deepak Narayanan,Luigi Nardi,Tian Zhao,Jian Zhang,Peter Bailis,Kunle Olukotun,Christopher Ré,Matei Zaharia +9 more
TL;DR: DAWNBENCH entries are analyzed to show that TTA has a low coefficient of variation and that models optimized for TTA generalize nearly as well as those trained using standard methods, and it is found that distributed entries can spend more than half of their time on communication.
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.