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
The Internet of Audio Things: State of the Art, Vision, and Challenges
TL;DR: The state of the art of this field is reviewed, then a vision for the IoAuT is presented, which enables the connection of digital and physical domains by means of appropriate information and communication technologies, fostering novel applications and services based on auditory information.
Journal ArticleDOI
A Generic Quality Control Framework for Fetal Ultrasound Cardiac Four-Chamber Planes
TL;DR: A generic deep learning framework for automatic quality control of fetal US cardiac four-chamber plane, which consists of a basic CNN, a deeper CNN, and the aggregated residual visual block net (ARVBNet), detecting the key anatomical structures on a plane is proposed.
Journal ArticleDOI
Automatic Land Cover Reconstruction From Historical Aerial Images: An Evaluation of Features Extraction and Classification Algorithms
TL;DR: A novel low-dimensional local texture filter named rotated-corner local binary pattern (R-CRLBP) is presented as a simplification of the binary gradient contours filter through the use of an orthogonal combination representation.
Journal ArticleDOI
Visual Localizer: Outdoor Localization Based on ConvNet Descriptor and Global Optimization for Visually Impaired Pedestrians.
TL;DR: This work proposes Visual Localizer, which is composed of ConvNet descriptor and global optimization, to achieve robust visual localization for assisted navigation and utilizes the network flow model as a global optimization of image matching.
Journal ArticleDOI
How Deep Should be the Depth of Convolutional Neural Networks: a Backyard Dog Case Study
Alexander N. Gorban,Alexander N. Gorban,Evgeny M. Mirkes,Evgeny M. Mirkes,Ivan Tyukin,Ivan Tyukin,Ivan Tyukin +6 more
TL;DR: This work proposed a simple non-iterative method for shallowing down pre-trained deep convolutional networks, generic in the sense that it applies to a broad class of feed-forward networks, and is based on the advanced supervise principal component analysis.
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.