返回
Progressive Channel-Shrinking Network
DOI:10.1109/TMM.2023.3291197.png)
摘要
En 中文
Currently, salience-based channel pruning makes continuous breakthroughs in network compression. In the realization, the salience mechanism is used as a metric of channel salience to guide pruning. Therefore, salience-based channel pruning can dynamically adjust the channel width at run-time, which provides a flexible pruning scheme. However, there are two problems emerging: a gating function is often needed to truncate the specific salience entries to zero, which destabilizes the forward propagation; dynamic architecture brings more cost for indexing in inference which bottlenecks the inference speed. In this article, we propose a Progressive Channel-Shrinking (PCS) method to compress the selected salience entries at run-time instead of roughly approximating them to zero. We also propose a Running Shrinking Policy to provide a testing-static pruning scheme that can reduce the memory access cost for filter indexing. We evaluate our method on ImageNet and CIFAR10 datasets over two prevalent networks: ResNet and VGG, and demonstrate that our PCS outperforms all baselines and achieves state-of-the-art in terms of compression-performance tradeoff. Moreover, we observe a significant and practical acceleration of inference. The code is available at https://github.com/JianhongPan-VLG/Progressive.Channel-Shrinking.Network.
Keyword:
Training
Indexing
Convolution
Costs
Generators
Feature extraction
Testing
Progressive
network shrinking
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
Molecular and Pharmacological Characterization of GABAA Receptors in the Rat Pituitary大鼠垂体中GABAA 受体的分子和药理学特征
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍?
Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors

