Data-Aware Adaptive Pruning Model Compression Algorithm Based on a Group Attention Mechanism and Reinforcement Learning

Data-Aware Adaptive Pruning Model Compression Algorithm Based on a Group Attention Mechanism and Reinforcement Learning

The success of convolutional neural networks (CNNs) benefits from the stacking of convolutional layers, which improves the model’s receptive field for image data but also causes a decrease in inference speed. To improve the inference speed of large convolutional network models without sac...

Full description

Bibliographic Details
Main Authors: Zhi Yang, Yuan Zhai, Yi Xiang, Jianquan Wu, Jinliang Shi, Ying Wu
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Model compression
pruning algorithm
attention mechanism
reinforcement learning
Online Access:https://ieeexplore.ieee.org/document/9813741/

Similar Items

Similar Items