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
Survey on Deep Neural Networks in Speech and Vision Systems
TL;DR: This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications from the perspectives of both software and hardware systems.
Journal ArticleDOI
A Survey on Visual Navigation for Artificial Agents With Deep Reinforcement Learning
TL;DR: Five main categories of visual DRL navigation are systematically described: direct DRL vNavigation, hierarchical DRL dRL v Navigation, multi-task D RL vNavigate, memory-inference DRLvNavigation and vision-language DRL cNavigation.
Posted Content
3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI
TL;DR: This work proposes a highly efficient 3D CNN to achieve real-time dense volumetric segmentation of brain MRI volumes that leverages the 3D multi-fiber unit which consists of an ensemble of lightweight 3D convolutional networks to significantly reduce the computational cost.
Proceedings ArticleDOI
Knowledge Distillation via Route Constrained Optimization
TL;DR: In this article, a route constrained optimization (RCO) operation is proposed to reduce the lower bound of congruence loss for knowledge distillation, hint and mimicking learning.
Posted Content
Edge Intelligence: Architectures, Challenges, and Applications
TL;DR: This survey article provides a comprehensive introduction to edge intelligence and its application areas and presents a systematic classification of the state of the solutions by examining research results and observations for each of the four components.
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.