Corpus ID: 209439693

Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks

@article{Kuzmin2019TaxonomyAE,
  title={Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks},
  author={Andrey Kuzmin and Markus Nagel and Saurabh Pitre and S. Pendyam and Tijmen Blankevoort and M. Welling},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.09802}
}
The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more efficient is neural network compression. We provide an overview of existing neural network compression methods that can be used to make neural networks more efficient by changing the architecture of the network. First, we introduce a new way to categorize all published compression methods, based on the amount of data… Expand
11 Citations
Learned Threshold Pruning
  • 5
  • PDF
Cyclic orthogonal convolutions for long-range integration of features
  • PDF
Skip-Convolutions for Efficient Video Processing
  • PDF
Differentiable Joint Pruning and Quantization for Hardware Efficiency
  • 5
  • PDF
Bayesian Bits: Unifying Quantization and Pruning
  • 9
  • PDF
Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX
  • Highly Influenced
Structured Convolutions for Efficient Neural Network Design
  • Highly Influenced
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 53 REFERENCES
Efficient Neural Network Compression
  • H. Kim, M. U. Khan, C. Kyung
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
  • 18
  • Highly Influential
  • PDF
Tensorizing Neural Networks
  • 472
  • PDF
Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
  • 9
  • Highly Influential
  • PDF
Ultimate tensorization: compressing convolutional and FC layers alike
  • 94
  • PDF
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
  • 519
  • Highly Influential
  • PDF
Speeding up Convolutional Neural Networks with Low Rank Expansions
  • 952
  • Highly Influential
  • PDF
Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
  • 4,444
  • PDF
Convolutional neural networks with low-rank regularization
  • 259
  • PDF
Automatic Rank Selection for High-Speed Convolutional Neural Network
  • 3
  • PDF
...
1
2
3
4
5
...