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
Review of Pavement Defect Detection Methods
Wenming Cao,Liu Qifan,Zhiquan He +2 more
TL;DR: The three types of 3D data representations are compared and the corresponding performance of the deep neural networks for 3D object detection is studied and compared in three ways, classification based, object detection based and segmentation based.
Journal ArticleDOI
Automated Detection of Autism Spectrum Disorder Using a Convolutional Neural Network.
Zeinab Sherkatghanad,Mohammadsadegh Akhondzadeh,Soorena Salari,Mariam Zomorodi-Moghadam,Moloud Abdar,U. Rajendra Acharya,U. Rajendra Acharya,U. Rajendra Acharya,Reza Khosrowabadi,Vahid Salari,Vahid Salari +10 more
TL;DR: The proposed model is able to detect ASD correctly with an accuracy of 70.22% using the ABIDE I dataset and the CC400 functional parcellation atlas of the brain and is hence computationally less intensive than state-of-art techniques.
Proceedings ArticleDOI
Two-Step Quantization for Low-bit Neural Networks
TL;DR: A simple yet effective Two-Step Quantization (TSQ) framework is proposed, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes, and the sparse quantization method for code learning.
Posted Content
An Entropy-based Pruning Method for CNN Compression
Jian-Hao Luo,Jianxin Wu +1 more
TL;DR: This paper aims to simultaneously accelerate and compress off-the-shelf CNN models via filter pruning strategy with the proposed entropy-based method, which can reduce the size of intermediate activations.
Posted Content
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks.
TL;DR: A comprehensive survey of recent advances in network acceleration, compression, and accelerator design from both algorithm and hardware points of view is provided.
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.