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
Manufacturing process monitoring using time-frequency representation and transfer learning of deep neural networks
TL;DR: The study finds that the multi-resolution capability of the CWT technique allows it to render more accurate and richer details of the signals, and shows that the classification accuracy can be improved by using shallower networks modified from the VGG-16 network to mitigate the overfitting issue.
Posted Content
IOS: Inter-Operator Scheduler for CNN Acceleration
TL;DR: This work extensively study the parallelism between operators and proposes Inter-Operator Scheduler (IOS) to automatically schedule the execution of multiple operators in parallel to accelerate CNN inference.
Journal ArticleDOI
Real-Time Classification of Rubber Wood Boards Using an SSR-Based CNN
TL;DR: This article presents a split-shuffle-residual (SSR)-based CNN that can learn features automatically from wood images for real-time classification of rubber wood boards and demonstrates that the algorithm outperforms other traditional classification methods and the state-of-the-art deep learning classification networks.
Proceedings Article
MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
TL;DR: Li et al. as discussed by the authors proposed a lightweight deep learning model for efficient COVID-19 segmentation, which has high computational efficiency and can be fast retrained by other users using their private COVID19 data for further improving performance.
Proceedings ArticleDOI
Development of a highly precise place recognition module for effective human-robot interactions in changing lighting and viewpoint conditions
TL;DR: A full end-to-end convolutional neural network architecture is developed, using a pre-trained deep convolved neural network and the explicit inductive bias transfer learning strategy to give the robot the ability to recognize its environment context.
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.