Corpus ID: 81978476

Dynamic Multi-path Neural Network

@article{Su2019DynamicMN,
  title={Dynamic Multi-path Neural Network},
  author={Ying-Cheng Su and Shunfeng Zhou and Y. Wu and Xuebo Liu and Tian Su and Ding Liang and J. Yan},
  journal={arXiv: Computer Vision and Pattern Recognition},
  year={2019}
}
  • Ying-Cheng Su, Shunfeng Zhou, +4 authors J. Yan
  • Published 2019
  • Computer Science
  • arXiv: Computer Vision and Pattern Recognition
  • Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. [...] Key Method The inference path of the network is determined by a controller, which takes into account both previous state and object category information. The proposed method can be easily incorporated into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate…Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES
    Deep Residual Learning for Image Recognition
    • 50,397
    • Highly Influential
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,416
    • PDF
    Going deeper with convolutions
    • 19,987
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,307
    • PDF
    Learning Multiple Layers of Features from Tiny Images
    • 9,081
    • PDF
    Aggregated Residual Transformations for Deep Neural Networks
    • 2,690
    • PDF
    MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
    • 5,061
    • Highly Influential
    • PDF
    Distilling the Knowledge in a Neural Network
    • 4,300
    • PDF