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
Towards Reverse-Engineering Black-Box Neural Networks
TL;DR: This paper showed that the revealed internal information helps generate more effective adversarial examples against the black-box model, which can be used for better protection of private content from automatic recognition models using adversarial example.
Journal ArticleDOI
FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks
Michaela Blott,Thomas B. Preußer,Nicholas J. Fraser,Giulio Gambardella,Kenneth O'Brien,Yaman Umuroglu,Miriam Leeser,Kees Vissers +7 more
TL;DR: The second generation of the FINN framework is described, an end-to-end tool that enables design-space exploration and automates the creation of fully customized inference engines on FPGAs that optimizes for given platforms, design targets, and a specific precision.
Proceedings ArticleDOI
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
Xiaoliang Dai,Yangqing Jia,Peter Vajda,Matthew T. Uyttendaele,Niraj K. Jha,Peizhao Zhang,Bichen Wu,Hongxu Yin,Fei Sun,Yanghan Wang,Marat Dukhan,Yunqing Hu,Yiming Wu +12 more
TL;DR: The results show that adapting computation resources to building blocks is critical to model performance, and a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors is proposed.
Posted Content
Data-Driven Sparse Structure Selection for Deep Neural Networks
Zehao Huang,Naiyan Wang +1 more
TL;DR: In this paper, a scaling factor is introduced to scale the outputs of specific structures, such as neurons, groups or residual blocks, and sparsity regularizations on these factors are added to solve this optimization problem by a modified Accelerated Proximal Gradient (APG) method.
Proceedings ArticleDOI
On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework
TL;DR: A usage-driven selection framework is developed, referred to as AdaDeep, to automatically select a combination of compression techniques for a given DNN, that will lead to an optimal balance between user-specified performance goals and resource constraints.
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.