ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

  title={ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions},
  author={H. Gao and Zhengyang Wang and S. Ji},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  • H. Gao, Zhengyang Wang, S. Ji
  • Published 2018
  • Computer Science, Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. [...] Key Method ChannelNets use three instances of channel-wise convolutions; namely group channel-wise convolutions, depth-wise separable channel-wise convolutions, and the convolutional classification layer. Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy. Notably…Expand Abstract
    19 Citations
    ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
    • 45
    • PDF
    Self-grouping Convolutional Neural Networks
    Deep Model Compression via Filter Auto-sampling
    • 1
    E2GC: Energy-efficient Group Convolution in Deep Neural Networks
    • 1
    • Highly Influenced
    • PDF
    Inner-Imaging Networks: Put Lenses into Convolutional Structure.
    NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
    • 2
    • PDF
    Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
    • 18


    Quantized Convolutional Neural Networks for Mobile Devices
    • 557
    • PDF
    Xception: Deep Learning with Depthwise Separable Convolutions
    • F. Chollet
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 3,272
    • PDF
    Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
    • 462
    • PDF
    Speeding up Convolutional Neural Networks with Low Rank Expansions
    • 871
    • PDF
    ImageNet classification with deep convolutional neural networks
    • 54,895
    • Highly Influential
    • PDF
    XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
    • 1,471
    • PDF
    Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
    • 3,846
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 41,191
    • Highly Influential
    • PDF
    ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
    • 1,706
    • Highly Influential
    • PDF
    Going deeper with convolutions
    • 20,823
    • PDF