2018

Trained Rank Pruning for Efficient Deep Neural Networks

Xu, Yuhui, Li, Yuxi, Zhang, Shuai et al.

Understand

The performance of Deep Neural Networks (DNNs) keeps elevating in recent years with increasing network depth and width.

  • To enable DNNs on edge devices like mobile phones, researchers proposed several network compression methods including pruning, quantization and factorization.
  • Among the factorization-based approaches, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.
  • Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple a large prediction loss.

Built on

  • Characterization of the subdifferential of some matrix norms

    G. A. Watson · 1992

    Earlier work this paper cites.

  • Imagenet: A large-scale hierarchical image database

    J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009

    Earlier work this paper cites.

  • Learning multiple layers of features from tiny images

    A. Krizhevsky and G. Hinton · 2009

    Earlier work this paper cites.

  • Efficient and practical stochastic subgradient descent for nuclear norm regularization

    H. Avron, S. Kale, S. P. Kasiviswanathan, and V. Sindhwani · 2012

    Earlier work this paper cites.

  • Exploiting linear structure within convolutional networks for efficient evaluation

    E. Denton, W. Zaremba, J. Bruna, Y. Lecun, and R. Fergus · 2014

    Earlier work this paper cites.

  • Speeding up convolutional neural networks with low rank expansions

    Original

    M. Jaderberg, A. Vedaldi, and A. Zisserman · 2014

    Earlier work this paper cites.

Similar

  • Compressing neural networks with the hashing trick

    W. Chen, J. Wilson, S. Tyree, K. Weinberger, and Y. Chen · 2015

    Cited alongside, same era.

  • Faster r-cnn: Towards real-time object detection with region proposal networks

    S. Ren, K. He, R. B. Girshick, and J. Sun · 2015

    Cited alongside, same era.

  • Deep residual learning for image recognition

    K. He, X. Zhang, S. Ren, and J. Sun · 2016

    Cited alongside, same era.

  • Pruning filters for efficient convnets

    Original

    H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf · 2016

    Cited alongside, same era.

  • Accelerating very deep convolutional networks for classification and detection

    X. Zhang, J. Zou, K. He, and J. Sun · 2016

    Cited alongside, same era.

  • Compression-aware training of deep networks

    J. M. Alvarez and M. Salzmann · 2017

    Cited alongside, same era.

Then

  • Channel pruning for accelerating very deep neural networks

    Y. He, X. Zhang, and J. Sun · 2017

    Later among the works it cites.

  • Thinet: A filter level pruning method for deep neural network compression

    J.-H. Luo, J. Wu, and W. Lin · 2017

    Later among the works it cites.

  • Coordinating filters for faster deep neural networks

    W. Wen, C. Xu, C. Wu, Y. Wang, Y. Chen, and H. Li · 2017

    Later among the works it cites.

  • Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs

    L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille · 2018

    Closest in time.

  • Network decoupling: From regular to depthwise separable convolutions

    J. Guo, Y. Li, W. Lin, Y. Chen, and J. Li · 2018

    Closest in time.

  • Thinet: pruning cnn filters for a thinner net

    J.-H. Luo, H. Zhang, H.-Y. Zhou, C.-W. Xie, J. Wu, and W. Lin · 2018

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…