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
Binarizing MobileNet via Evolution-Based Searching
TL;DR: In this article, a group convolutional neural network (G-CNN) was used to find a good set of hyper-parameters for group convolutions, which leverages the exploration of efficient 1-bit models.
Proceedings ArticleDOI
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
TL;DR: In this paper, sparse feature reactivation (SFR) is proposed to increase the utility of features for reusing in deep networks through dense connectivity, which achieves promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO).
Journal ArticleDOI
Analyzing and mitigating data stalls in DNN training
TL;DR: In this paper, the authors explored many different ways of reducing DNN training time and the impact of input data pipeline on the performance of DNNs, and proposed a method to reduce the training time of deep neural networks.
Journal ArticleDOI
IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices
Tom Lawrence,Li Zhang +1 more
TL;DR: IoTNet is proposed, a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models and is benchmarked against state- of- the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource- Conventional IoT environments.
Journal ArticleDOI
Benchmarking lightweight face architectures on specific face recognition scenarios
Yoanna Martínez-Díaz,Miguel Nicolás-Díaz,Heydi Méndez-Vázquez,Luis S. Luevano,Leonardo Chang,Miguel González-Mendoza,Luis Enrique Sucar +6 more
TL;DR: This paper studies the impact of lightweight face models on real applications and evaluates the performance of five recent lightweight architectures on five face recognition scenarios: image and video based face recognition, cross-factor and heterogeneous face Recognition, as well as active authentication on mobile devices.
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.