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
Ensemble residual network-based gender and activity recognition method with signals
TL;DR: A novel ResNet-based signal recognition method using ResNet18, ResNet50 and ResNet101 as feature extractor and each network extracts 1000 features that achieved high success rate for sensors signals.
Journal ArticleDOI
A Low Effort Approach to Structured CNN Design Using PCA
TL;DR: This work proposes a method to analyze a trained network and deduce an optimized, compressed architecture that preserves accuracy while keeping computational costs tractable, by using PCA (Principal Component Analysis).
Journal ArticleDOI
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT
TL;DR: Network of Neural Networks (NoNN) as discussed by the authors proposes a new distributed IoT learning paradigm that compresses a large pretrained "teacher" deep network into several disjoint and highly-compressed "student" modules, without loss of accuracy.
Journal ArticleDOI
An ensemble of deep neural networks for kidney ultrasound image classification.
S. Sudharson,Priyanka Kokil +1 more
TL;DR: This paper proposes an automatic classification of B-mode kidney ultrasound images based on the ensemble of deep neural networks (DNNs) using transfer learning and proves its superiority when compared to the conventional and DNN based classification methods.
Patent
Generation of video from spherical content using edit maps
TL;DR: In this article, a spherical video sharing platform enables users to share the captured spherical content and enable users to access spherical content shared by other users by using captured metadata or video/audio processing.
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.