Pruning Filter via Geometric Median for Deep Convolutional Neural Networks Acceleration

By Yang He, Ping Liu, Ziwei Wang, Yi Yang. 2018

37 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yang He
2. Linchao Zhu
3. Yi Yang
4. Shaohui Lin
5. Rongrong Ji
6. Baochang Zhang
7. Ping Liu
8. Qixiang Ye

Citations in the corpus

• Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks (2019, unknown): “82 FPGM [13] 7 74.”
• Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks (2019, methodology): “Now, here arises two questions: (1) considering the promising results of Relational Criterion, is there any other measurement, except Geometric Median utilized in [14], can be employed for Relational Criterion; (2) as the filter distribution keeps changing during the training (pruning) process, is i”
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning (2019, methodology): “To address these issues, techniques have been proposed for CNN compression such as low-rank decomposition [3, 58, 33, 32], parameter quantization [42, 23, 59], knowledge distillation [17, 45] and network pruning [10, 31, 35, 21, 15, 34].”