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
Single Path One-Shot Neural Architecture Search with Uniform Sampling
TL;DR: In this paper, the authors proposed a single path one-shot neural architecture search (NAS) model, where all architectures are single paths so that weight co-adaption problem is alleviated.
Journal ArticleDOI
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
S. Kevin Zhou,Hayit Greenspan,Christos Davatzikos,James S. Duncan,Bram van Ginneken,Anant Madabhushi,Jerry L. Prince,Daniel Rueckert,Ronald M. Summers +8 more
TL;DR: This survey article presents traits of medical imaging, highlights both clinical needs and technical challenges in medical Imaging, and describes how emerging trends in DL are addressing these issues, including the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, and so on.
Proceedings ArticleDOI
Rethinking Classification and Localization for Object Detection
TL;DR: In this paper, the authors proposed a Double-Head method, which has a fully connected head focusing on classification and a convolution head for bounding box regression, achieving an accuracy of +3.5 and +2.8 AP on MS COCO dataset from Feature Pyramid Network (FPN) baselines with ResNet-50 and ResNet101 backbones, respectively.
Journal ArticleDOI
ThiNet: Pruning CNN Filters for a Thinner Net
TL;DR: It is revealed that the original VGG-16 model can be compressed into a very small model (ThiNet-Tiny) with only 2.66 MB model size, but still preserve AlexNet level accuracy, and “gcos” (Group COnvolution with Shuffling), a more accurate group convolution scheme, to further reduce the pruned model size.
Proceedings ArticleDOI
Towards Effective Low-Bitwidth Convolutional Neural Networks
TL;DR: In this article, a two-stage optimization strategy is proposed to find good local minima and then a progressive optimization approach is adopted to progressively decrease the bit-width during the course of training.
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.