Multisource Mobile Transfer Learning Algorithm Based on Dynamic Model Compression

• Published in: Security and communication networks Vol. 2022; pp. 1 - 12
• Main Authors: Gao, Peng, Li, Jingmei, Ding, Changhong
• Format: Journal Article
• Language: English
• Published: London Hindawi 16.03.2022; John Wiley & Sons, Inc; Hindawi Publishing Corporation
• Subjects: Accuracy; Algorithms; Cell phones; Classification; Cloud computing; Computer vision; Data encryption; Data transmission; Deep learning; Domains; Dynamic models; Electronic devices; Energy consumption; Image classification; Internet of Things; Machine learning; Mobile computing; Neural networks; Object recognition; R&D; Research & development; Storage
• ISSN: 1939-0114; 1939-0122; 1939-0122
• DOI: 10.1155/2022/3234078

With the development of the Internet of Things, the application of computer vision on mobile phones is becoming more and more extensive and people have higher and higher requirements for the timeliness of the recognition results returned and the processing capabilities of the mobile phone for image recognition. However, the processing capability and storage capability of the user terminal equipment cannot meet the needs of identifying and storing a large number of pictures, and the data transmission process will cause high energy consumption of the terminal equipment. At the same time, multisource deep transfer learning has outstanding performance in computer vision and image classification. However, due to the huge amount of calculation of the deep network model, it is impossible to use the existing excellent network model to realize image recognition and classification on the mobile terminal. In order to solve the abovementioned problems, we propose a multisource mobile transfer learning algorithm based on dynamic model compression, this algorithm considers the realization of multisource transfer learning computing in the case of multiple mobile device computing source domains, and the method also guarantees data privacy and security for each device (origin domain). Meanwhile, extensive experiments show that our method can achieve remarkable results in popular image classification datasets.