AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inference

• Published in: Pattern recognition Vol. 107; p. 107461
• Main Authors: Luo, Jian-Hao, Wu, Jianxin
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2020
• Subjects: CNN acceleration; Model compression; Neural network pruning; CNN acceleration; Neural network pruning; Model compression

•Filter selection and model fine-tuning are integrated into a single end-to-end trainable framework.•Adaptive compression ratio and multi-layer compression.•Good generalization ability. Channel pruning is an important method to speed up CNN model’s inference. Previous filter pruning algorithms regar...