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
Proceedings ArticleDOI
Cloud-Based or On-Device: An Empirical Study of Mobile Deep Inference
TL;DR: This paper empirically evaluates the inference performance of three Convolutional Neural Networks using a benchmark Android application developed and suggests that on-device inference can cost up to two orders of magnitude greater response time and energy when compared to cloud-based inference, and that loading model and computing probability are two performance bottlenecks for on- device deep inferences.
Posted Content
Unite the People: Closing the Loop Between 3D and 2D Human Representations
Christoph Lassner,Javier Romero,Martin Kiefel,Federica Bogo,Michael J. Black,Peter V. Gehler +5 more
TL;DR: In this article, a hybrid approach is proposed to obtain high quality 3D body model fits for multiple human pose datasets, which leads to an initial dataset, UP-3D, with rich annotations.
Journal ArticleDOI
ShipDeNet-20: An Only 20 Convolution Layers and <1-MB Lightweight SAR Ship Detector
Tianwen Zhang,Xiaoling Zhang +1 more
TL;DR: Experimental results on the open SAR ship detection data set (SSDD) reveal that the accuracy and speed of ShipDeNet-20 are both superior to the other nine state-of-the-art object detectors.
Proceedings ArticleDOI
EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
TL;DR: Encrypted Vector Arithmetic (EVA) as discussed by the authors is an FHE language that includes an optimizing compiler that generates correct and secure FHE programs, while hiding all the complexities of the target FHE scheme.
Journal ArticleDOI
Deep Learning for Ultrasound Image Formation: CUBDL Evaluation Framework and Open Datasets.
Dongwoon Hyun,Alycen Wiacek,Sobhan Goudarzi,Sven Rothlubbers,Amir Asif,Klaus Eickel,Yonina C. Eldar,Jiaqi Huang,Massimo Mischi,Hassan Rivaz,David Sinden,Ruud J. G. van Sloun,Hannah Strohm,Muyinatu A. Lediju Bell +13 more
TL;DR: The CUBDL Task 1 dataset as discussed by the authors was used for the ultrasound beamforming with deep learning (CUBDL) challenge, which was offered as a component of the 2020 IEEE International Ultrasonics Symposium.
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.