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
Posted Content
Co-Design of Deep Neural Nets and Neural Net Accelerators for Embedded Vision Applications
TL;DR: It is shown that there are significant improvements available if deep neural net models and neural net accelerators are co-designed.
Journal ArticleDOI
DeepSearch: A Fast Image Search Framework for Mobile Devices
TL;DR: A fast image search framework, named DeepSearch, which makes complex image search based on CNNs feasible on mobile phones and significantly speed up the CNN models and further makes CNN-based image search practical on common smart phones.
Posted Content
Least squares binary quantization of neural networks
TL;DR: This work introduces a novel 2-bits quantization with provably least squares error, and provides a unified framework to analyze different scaling strategies on the binary quantization, in which values are mapped to -1 and 1.
Journal ArticleDOI
Brain tumor classification using the fused features extracted from expanded tumor region
TL;DR: In this paper, a brain tumor classification method using the fusion of deep and shallow features is proposed to distinguish between meningioma, glioma and pituitary tumor types and to predict the 1p/19q co-deletion status of LGG tumors.
Journal ArticleDOI
HetConv: Beyond Homogeneous Convolution Kernels for Deep CNNs
TL;DR: The proposed Heterogeneous Kernel-Based Convolution (HetConv) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while it maintains representational efficiency and accuracy.
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.