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
1.2 Intelligence on Silicon: From Deep-Neural-Network Accelerators to Brain Mimicking AI-SoCs
TL;DR: Artificial-Intelligence technology is widely used in most information hardware, software, and networking, underlying all consumer technology: smartphones, home appliances, and the Web.
Journal ArticleDOI
Image-based segmentation and quantification of weak interlayers in rock tunnel face via deep learning
Jiayao Chen,Dongming Zhang,Hongwei Huang,Mahdi Shadabfar,Mahdi Shadabfar,Mingliang Zhou,Tongjun Yang +6 more
TL;DR: An advanced integrated pixel-level method based on the deep convolutional neural network (DCNN) approach named DeepLabv3+ is proposed for weak interlayers detection and quantification that can efficiently segment damage for rock tunnel faces, eliminate more noises, and consequently provide a much faster running speed.
Proceedings ArticleDOI
Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
TL;DR: In this article, a contrastive learning approach was proposed to learn a metric to differentiate normal driving from anomalous driving, which achieved a 0.9673 AUC on the test set.
Journal ArticleDOI
A dual attention network based on efficientNet-B2 for short-term fish school feeding behavior analysis in aquaculture
TL;DR: Wang et al. as discussed by the authors proposed a dual attention network with EfficientNet-B2 for fine-grained short-term feeding behavior analysis of fish school, which includes two parallel attention modules, which focus on the feature extraction of the feeding region.
Posted Content
Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
TL;DR: This work introduces a new way to categorize all published compression methods, based on the amount of data and compute needed to make the methods work in practice, and shows that SVD and probabilistic compression or pruning methods are complementary and give the best results of all the considered 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.