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
Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations
TL;DR: A feature representation based layer-wise pruning method that aims at reducing complex CNNs to more compact ones with equivalent performance and is able to significantly reduce computational cost and the pruned models achieve equivalent or even better performance compared to the original models on various datasets.
Journal ArticleDOI
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
TL;DR: The authors propagate the real-valued activations generated by each 1-bit convolution via a parameter-free shortcut to enhance the representational capability of the network and achieve state-of-the-art performance.
Journal ArticleDOI
A Survey of the Recent Architectures of Deep Convolutional Neural Networks
TL;DR: Deep Convolutional Neural Networks (CNNs) as mentioned in this paper are a special type of Neural Networks, which has shown exemplary performance on several competitions related to Computer Vision and Image Processing.
Journal ArticleDOI
ESFNet: Efficient Network for Building Extraction From High-Resolution Aerial Images
TL;DR: Compared to available deep learning models, the proposed ARC-Net demonstrates better segmentation performance with less computational costs and is both effective and efficient in automatic building extraction from high-resolution aerial images.
Journal ArticleDOI
A critical review and comparative study on image segmentation-based techniques for pavement crack detection
TL;DR: The most common rule-driven-based and data-driven image segmentation algorithms are compared and discussed in this article , and strategies to obtain better results such as hybrid integration algorithms and optimization methods are presented.
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.