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
Journal ArticleDOI
Underwater image enhancement with global–local networks and compressed-histogram equalization
Xueyang Fu,Xiangyong Cao +1 more
TL;DR: This work proposes a two-branch network to compensate the global distorted color and local reduced contrast, respectively, and designs a compressed-histogram equalization to complement the data-driven deep learning, in which the parameters are fixed after training.
Proceedings ArticleDOI
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
TL;DR: Group-Net as discussed by the authors proposes a network decomposition strategy, in which the network is divided into groups and each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches.
Posted Content
Timeception for Complex Action Recognition
TL;DR: Timeception as discussed by the authors uses multi-scale temporal convolutions and reduces the complexity of 3D convolutions, which achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS.
Proceedings ArticleDOI
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
Zheng Zhu,Guan Huang,Jiankang Deng,Yun Ye,Junjie Huang,Xinze Chen,Jiagang Zhu,Tian Yang,Jiwen Lu,Dalong Du,Jie Zhou +10 more
TL;DR: Wang et al. as discussed by the authors proposed a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2m identities/42M faces(WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Posted Content
SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecture
Kevin Trebing,Siamak Mehrkanoon +1 more
TL;DR: This work proposes SmaAt-UNet, an efficient convolutional neural networks based on the well known UNet architecture equipped with attention modules and depthwise-separable convolutions that is comparable to other examined models while only using a quarter of the trainable parameters.
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.