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
Tiny Defect Detection in High-Resolution Aero-Engine Blade Images via a Coarse-to-Fine Framework
TL;DR: In this article, a coarse-to-fine framework was proposed for aero-engine blade surface defect detection in large-scale images, which can effectively save computation and improve accuracy.
Journal ArticleDOI
On Improving the accuracy with Auto-Encoder on Conjunctivitis
TL;DR: The results show that the proposed AE-based model can not only improve the classification accuracy but also be beneficial to solve the problem of False Positive Rate.
Journal ArticleDOI
Energy-Quality Scalable Integrated Circuits and Systems: Continuing Energy Scaling in the Twilight of Moore’s Law
TL;DR: This paper aims to take stock of recent advances in the field of energy-quality scalable circuits and systems, as promising direction to continue the historical exponential energy downscaling under diminished returns from technology and voltage scaling.
Book ChapterDOI
NetScore: Towards Universal Metrics for Large-Scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage
TL;DR: In this article, the authors proposed a new balanced metric called NetScore, which is designed specifically to provide a quantitative assessment of the balance between accuracy, computational complexity, and network architecture complexity of a deep neural network.
Proceedings ArticleDOI
Trends in deep convolutional neural Networks architectures: a review
TL;DR: This paper presents a survey of recent advances in CNN architecture design taking into account the three periods listed above, and discusses what is the theory behind building CNN models combining some components.
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.