Knowledge Distillation: A Survey
Autor: | Baosheng Yu, Stephen J. Maybank, Jianping Gou, Dacheng Tao |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computational complexity theory Computer science Machine Learning (stat.ML) 02 engineering and technology ENCODE Machine Learning (cs.LG) law.invention Statistics - Machine Learning Artificial Intelligence law 0202 electrical engineering electronic engineering information engineering Architecture Distillation csis business.industry Deep learning Data science Variety (cybernetics) Pattern recognition (psychology) Scalability 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business Software |
Zdroj: | International Journal of Computer Vision. 129:1789-1819 |
ISSN: | 1573-1405 0920-5691 |
Popis: | In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded. It has been accepted for publication in International Journal of Computer Vision (2021) |
Databáze: | OpenAIRE |
Externí odkaz: |