Corpus ID: 220403644

Operation-Aware Soft Channel Pruning using Differentiable Masks

@inproceedings{Kang2020OperationAwareSC,
  title={Operation-Aware Soft Channel Pruning using Differentiable Masks},
  author={Minsoo Kang and B. Han},
  booktitle={ICML},
  year={2020}
}
We propose a simple but effective data-driven channel pruning algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. The proposed approach makes a joint consideration of batch normalization (BN) and rectified linear unit (ReLU) for channel pruning; it estimates how likely the two successive operations deactivate each feature map and prunes the channels with high probabilities. To this end, we learn differentiable masks for… Expand
Pruning by Training: A Novel Deep Neural Network Compression Framework for Image Processing
DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
Effective Sparsification of Neural Networks with Global Sparsity Constraint
Carrying out CNN Channel Pruning in a White Box
Learning Efficient GANs using Differentiable Masks and co-Attention Distillation
Emerging Paradigms of Neural Network Pruning
Convolutional Neural Network Pruning with Structural Redundancy Reduction
  • Z. Wang, Chengcheng Li, Xiangyang Wang
  • Computer Science
  • ArXiv
  • 2021
...
1
2
...

References

SHOWING 1-10 OF 38 REFERENCES
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Channel Pruning for Accelerating Very Deep Neural Networks
  • Yihui He, X. Zhang, Jian Sun
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
Data-Driven Sparse Structure Selection for Deep Neural Networks
Variational Convolutional Neural Network Pruning
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
Model compression via distillation and quantization
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Speeding up Convolutional Neural Networks with Low Rank Expansions
Learning Structured Sparsity in Deep Neural Networks
...
1
2
3
4
...