XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

@article{Rastegari2016XNORNetIC,
  title={XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks},
  author={M. Rastegari and Vicente Ordonez and Joseph Redmon and Ali Farhadi},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.05279}
}
  • M. Rastegari, Vicente Ordonez, +1 author Ali Farhadi
  • Published 2016
  • Computer Science
  • ArXiv
  • We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. [...] Key Result This results in 58\(\times \) faster convolutional operations (in terms of number of the high precision operations) and 32\(\times \) memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our…Expand Abstract
    Towards Accurate Binary Convolutional Neural Network
    • 248
    • Highly Influenced
    • PDF
    Trained Ternary Quantization
    • 564
    • Highly Influenced
    • PDF
    Pruning Filters for Efficient ConvNets
    • 1,167
    • PDF
    MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
    • 5,061
    • PDF
    Local Binary Convolutional Neural Networks
    • 116
    • PDF
    ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
    • 1,581
    • PDF
    FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
    • 377
    • PDF
    Recent advances in convolutional neural networks
    • 935
    • PDF
    Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
    • 118
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES
    ImageNet classification with deep convolutional neural networks
    • 52,359
    • Highly Influential
    • PDF
    Deep Residual Learning for Image Recognition
    • 50,397
    • Highly Influential
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,416
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,452
    • PDF
    Going deeper with convolutions
    • 19,987
    • Highly Influential
    • PDF
    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
    • 18,896
    • PDF
    BinaryConnect: Training Deep Neural Networks with binary weights during propagations
    • 1,496
    • Highly Influential
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,201
    • PDF
    Network In Network
    • 3,001
    • PDF
    Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
    • 3,671
    • PDF