Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks

Cited 22 time in webofscience Cited 0 time in scopus
  • Hit : 28
  • Download : 0
Deep neural models, in recent years, have been successful in almost every field. However, these models are huge, demanding heavy computation power. 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.
Publisher
IEEE COMPUTER SOC
Issue Date
2022-06
Language
English
Article Type
Review
Citation

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.44, no.6, pp.3048 - 3068

ISSN
0162-8828
DOI
10.1109/TPAMI.2021.3055564
URI
http://hdl.handle.net/10203/296684
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 22 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0