期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 44, 期 6, 页码 3048-3068出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3055564
关键词
Training; Measurement; Computational modeling; Visualization; Task analysis; Knowledge transfer; Speech recognition; Knowledge distillation (KD); student-teacher learning (S-T); deep neural networks (DNN); visual intelligence
资金
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [NRF-2018R1A2B3008640]
- Institute of Information and Communications Technology Planning & Evaluation (IITP) - Korea Government (MSIT) [2020-0-00440]
This paper discusses the recent progress of knowledge distillation (KD) and student-teacher (S-T) learning, providing a comprehensive survey of KD methods and commonly used S-T frameworks for vision tasks. The study summarizes the working principles and effectiveness of KD, and analyzes the research status of KD in vision applications. Finally, it explores the potential developments and future directions of KD and S-T learning.
Deep neural models, in recent years, have been successful in almost every field, even solving the most complex problem statements. However, these models are huge in size with millions (and even billions) of parameters, demanding heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of labeled data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called 'Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically used for vision tasks. In general, we investigate some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据