Learning From Teacher’s Failure: A Reflective Learning Paradigm for Knowledge Distillation-Reference-Cited by-同舟云学术

Learning From Teacher’s Failure: A Reflective Learning Paradigm for Knowledge Distillation

Published:2024-01 Issue:1 Volume:34 Page:384-396
ISSN:1051-8215
Container-title:IEEE Transactions on Circuits and Systems for Video Technology
language:
Short-container-title:IEEE Trans. Circuits Syst. Video Technol.

Author:

Xu Kai¹^ORCID,Wang Lichun¹^ORCID,Xin Jianjia¹^ORCID,Li Shuang¹^ORCID,Yin Baocai¹^ORCID

Affiliation:

1. Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Beijing Natural Science Foundation

Foundation for China University Industry-University-Research Innovation

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Link

http://xplorestaging.ieee.org/ielx7/76/10382161/10148979.pdf?arnumber=10148979

Reference44 articles.

1. GL-RG: Global-Local Representation Granularity for Video Captioning

2. SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation

3. TF-Blender: Temporal Feature Blender for Video Object Detection

4. Distilling the knowledge in a neural network;Hinton;arXiv:1503.02531,2015

5. Faster CNNs with direct sparse convolutions and guided pruning;Park;arXiv:1608.01409,2016

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Multi-level knowledge distillation via dynamic decision boundaries exploration and exploitation;Information Fusion;2024-12

2. Collaborative Knowledge Distillation;IEEE Transactions on Circuits and Systems for Video Technology;2024-08

3. Self-Knowledge Distillation with Learning from Role-Model Samples;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14