ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Xiangyu Zhang,Xinyu Zhou,Mengxiao Lin,Jian Sun +3 more
- pp 6848-6856
Reads0
Chats0
TLDR
ShuffleNet as discussed by the authors utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy, and achieves an actual speedup over AlexNet while maintaining comparable accuracy.Abstract:
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet [12] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13A— actual speedup over AlexNet while maintaining comparable accuracy.read more
Citations
More filters
Journal ArticleDOI
Designing a lightweight 1D convolutional neural network with Bayesian optimization for wheel flat detection using carbody accelerations
TL;DR: A 1D lightweight Convolutional Neural Network architecture, i.e. LightWFNet, guided by Bayesian Optimization for wheel flat (WF) detection, validated for WF detection by using carbody accelerations with much lower computational costs.
Proceedings ArticleDOI
A Lightweight Deep Learning Model for COVID-19 Detection
TL;DR: A lightweight deep learning model suitable to be implemented for fast screening purposes so that better-targeted diagnoses can be performed to optimize the test time and cost is proposed.
Journal ArticleDOI
FPGA-Based Hybrid-Type Implementation of Quantized Neural Networks for Remote Sensing Applications
TL;DR: A symmetric quantization scheme-based hybrid-type inference method was proposed, which uses the low bit-width integer to replace floating-point precision, and a training approach for the quantized network is introduced to reduce accuracy degradation.
Posted Content
Slim-CNN: A Light-Weight CNN for Face Attribute Prediction.
Ankit Sharma,Hassan Foroosh +1 more
TL;DR: A computationally-efficient CNN micro-architecture Slim Module is introduced to design a lightweight deep neural network, Slim-CNN, for face attribute prediction, which achieves an accuracy of 91.24% and has a very low memory footprint, making it suitable for mobile and embedded applications.
Journal ArticleDOI
Towards efficient unconstrained handwriting recognition using Dilated Temporal Convolution Network
TL;DR: A fully convolution based deep network architecture for cursive handwriting recognition from line level images that has fewer parameters and takes less training and testing time, making it suitable for low-resource and environment-friendly deployment.
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.