LCNN: Lookup-Based Convolutional Neural Network

@article{Bagherinezhad2017LCNNLC,
  title={LCNN: Lookup-Based Convolutional Neural Network},
  author={Hessam Bagherinezhad and M. Rastegari and A. Farhadi},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={860-869}
}
  • Hessam Bagherinezhad, M. Rastegari, A. Farhadi
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary… CONTINUE READING
    ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
    • 1,580
    • PDF
    Channel Pruning for Accelerating Very Deep Neural Networks
    • 783
    • PDF
    Recent advances in convolutional neural networks
    • 935
    • PDF
    AMC: AutoML for Model Compression and Acceleration on Mobile Devices
    • 400
    • PDF
    The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
    • 200
    • PDF
    Packing Convolutional Neural Networks in the Frequency Domain
    • 101
    • PDF
    Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
    • 110
    • PDF
    Adaptive Neural Networks for Efficient Inference
    • 86
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES
    ImageNet classification with deep convolutional neural networks
    • 52,343
    • PDF
    Deep Residual Learning for Image Recognition
    • 50,343
    • Highly Influential
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,394
    • PDF
    Going deeper with convolutions
    • 19,981
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,443
    • PDF
    Fast R-CNN
    • 8,818
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,437
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,195
    • PDF
    Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
    • 3,669
    • PDF
    Understanding the difficulty of training deep feedforward neural networks
    • 8,515
    • PDF