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
DOTS: Decoupling Operation and Topology in Differentiable Architecture Search.
TL;DR: The proposed Decouple the Operation and Topology Search (DOTS), which decouples the topology representation from operation weights and makes an explicit topology search, and is an effective solution for differentiable NAS.
Proceedings ArticleDOI
AOGNets: Compositional Grammatical Architectures for Deep Learning
TL;DR: AOGNets as mentioned in this paper uses AND-OR Grammar (AOG) as a network generator for improving performance of deep neural networks (DNNs), which harness the best of two worlds: grammar models and DNNs.
Journal ArticleDOI
Steel Surface Defect Recognition: A Survey
TL;DR: A literature review of the algorithms related to steel surface defect recognition, which includes traditional machine learning algorithms based on texture features and shape features as well as supervised, unsupervised, and weakly supervised deep learning algorithms (incomplete supervision, inexact supervision, imprecise supervision) is presented in this article .
Book ChapterDOI
Deep Networks for Image-to-Image Translation with Mux and Demux Layers
TL;DR: A lightweight end–to–end deep learning approach for image enhancement that could improve both the quantitative and qualitative assessments, as well as the performance, and gets the third place in PIRM Enhancement–On–Smartphones Challenge 2018.
Posted Content
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
TL;DR: An adaptive fractional dilated convolution (AFDC) is developed, which is aspect-ratio-embedded, composition-preserving and parameter-free, which can be easily implemented by common deep learning libraries and plugged into popular CNN architectures in a computation-efficient manner.
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.