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
Proceedings ArticleDOI
Universally Slimmable Networks and Improved Training Techniques
Jiahui Yu,Thomas S. Huang +1 more
TL;DR: Yu et al. as discussed by the authors proposed a systematic approach to train universally slimmable networks (US-Nets), which can execute at arbitrary width, and generalize to networks both with and without batch normalization layers.
Journal ArticleDOI
Pan-cancer image-based detection of clinically actionable genetic alterations
Jakob Nikolas Kather,Jakob Nikolas Kather,Lara R. Heij,Lara R. Heij,Heike I. Grabsch,Heike I. Grabsch,Chiara Loeffler,Amelie Echle,Hannah Sophie Muti,Jeremias Krause,Jan M. Niehues,Kai A. J. Sommer,Peter Bankhead,Loes F. S. Kooreman,Jefree J. Schulte,Nicole A. Cipriani,Roman D. Buelow,Peter Boor,Nadina Ortiz-Brüchle,Andrew M. Hanby,Valerie Speirs,Sara Kochanny,Akash Patnaik,Andrew Srisuwananukorn,Hermann Brenner,Michael Hoffmeister,Piet A. van den Brandt,Dirk Jäger,Christian Trautwein,Alexander T. Pearson,Tom Luedde +30 more
TL;DR: The findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eosin.
Proceedings ArticleDOI
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
TL;DR: Hessian AWare Quantization (HAWQ), a novel second-order quantization method that allows for the automatic selection of the relative quantization precision of each layer, based on the layer's Hessian spectrum, is introduced.
Posted Content
Hello Edge: Keyword Spotting on Microcontrollers
TL;DR: It is shown that it is possible to optimize these neural network architectures to fit within the memory and compute constraints of microcontrollers without sacrificing accuracy, and the depthwise separable convolutional neural network (DS-CNN) is explored and compared against other neural network architecture.
Proceedings ArticleDOI
RepVGG: Making VGG-style ConvNets Great Again
TL;DR: RepVGG as mentioned in this paper decouples the training-time and inference-time architecture by a structural re-parameterization technique and achieves state-of-the-art accuracy on ImageNet.
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.