Adaptive high-precision compression method and system based on convolutional neural network model

US12380331B2 · kind B2 · utility

Assignees

• CHONGQING UNIVERSITY · CN
• University of Electronic Science and Technology of China · CN
• Dibi (Chongqing) Intelligent Technology Research Institute Co., Ltd. · CN
• Star Institute of Intelligent Systems · CN

Inventors

• Yongduan Song · Chongqing, CN
• Feng Yang · Chengdu, CN
• Rui Li · Los Angeles, US
• Shengtao Pan · Chongqing, CN
• Siyu Li · Guangyuan, CN
• Yiwen Zhang · Chongqing, CN
• Jian Zhang · Jinan, CN
• Zhengtao Yu · Mountain View, US
• Shichun Wang · Chongqing, CN

Key dates

• Filing date: Sep 27, 2021
• Grant date: Aug 5, 2025
• Expiry date: Jun 6, 2044

Classification

• Technology area (CPC Y): Emerging Cross-Sectional Technologies
• CPC primary: Y02D10/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The present disclosure discloses an adaptive high-precision compression method and system based on a convolutional neural network model, and belongs to the fields of artificial intelligence, computer vision, and image processing. According to the method of the present disclosure, coarse-grained pruning is performed on a neural network model by using a differential evolution algorithm first, and the coarse-grained space is quickly searched through an entropy importance criterion and an objective function with good guidance to obtain a near-optimal neural network structure. Then fine-grained search space is built on the basis of an optimal individual obtained from the coarse-grained search, and fine-grained pruning is performed on the neural network model by a differential evolution algorithm to obtain a network model with an optimal structure. Finally, the performance of the optimal model is restored by using a multi-teacher multi-step knowledge distillation network to reach the precision of an original model.