ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
arXiv:1707.01083
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 on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distilling the Knowledge in a Neural Network
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Fully Convolutional Networks for Semantic Segmentation
- Going Deeper with Convolutions
- Searching for Activation Functions
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Learning Structured Sparsity in Deep Neural Networks
- Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- Fast Convolutional Nets With fbfft: A GPU Performance Evaluation
- PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- Show and Tell: A Neural Image Caption Generator
- Interleaved Group Convolutions for Deep Neural Networks
- Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial "Bottleneck" Structure