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
Asymmetric metric learning for knowledge transfer
Mateusz Budnik,Yannis Avrithis +1 more
TL;DR: Inspired by an asymmetric testing task, asymmetric metric learning is introduced, a novel paradigm of using asymmetric representations at training that works best in symmetric testing, allowing the student to even out-perform the teacher.
Journal ArticleDOI
Classification of White blood cell using Convolution Neural Network
TL;DR: The classification of White Blood Cell using a Convolution Neural Network (CNN) is proposed and is able to classify the type of cell in much less epochs/time than other approaches.
Proceedings ArticleDOI
Lightweight network architecture for real-time action recognition
TL;DR: This work presents a new efficient approach to Human Action Recognition called Video Transformer Network (VTN), which leverages the latest advances in Computer Vision and Natural Language Processing and applies them to video understanding to create lightweight CNN models that achieve high accuracy and real-time speed.
Book ChapterDOI
Dynamic Group Convolution for Accelerating Convolutional Neural Networks.
TL;DR: Zhuo et al. as mentioned in this paper proposed dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly.
Journal ArticleDOI
Coarse-to-fine object detection in unmanned aerial vehicle imagery using lightweight convolutional neural network and deep motion saliency
TL;DR: Experimental results demonstrate that the proposed coarse-to-fine object detection method for UAV imagery using lightweight convolutional neural network (CNN) and deep motion saliency can achieve comparable detection speed but superior accuracy to six state-of-the-art methods.
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.