Layer‐wise hint‐based training for knowledge transfer in a teacher‐student framework
We devise a layer‐wise hint training method to improve the existing hint‐based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher‐student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively tr...
Main Authors: | Ji‐Hoon Bae, Junho Yim, Nae‐Soo Kim, Cheol‐Sig Pyo, Junmo Kim |
---|---|
Format: | Article |
Language: | English |
Published: |
Electronics and Telecommunications Research Institute (ETRI)
2019-01-01
|
Series: | ETRI Journal |
Subjects: | |
Online Access: | https://doi.org/10.4218/etrij.2018-0152 |
Similar Items
-
Technical hints
by: Editorial Team
Published: (2013-09-01) -
Adversarial Optimization-Based Knowledge Transfer of Layer-Wise Dense Flow for Image Classification
by: Doyeob Yeo, et al.
Published: (2021-04-01) -
Contextual factors affecting hint utility
by: Paul Salvador Inventado, et al.
Published: (2018-04-01) -
Automated Data-Driven Hint Generation for Learning Programming
by: Rivers, Kelly
Published: (2017) -
Sensitivity-Oriented Layer-Wise Acceleration and Compression for Convolutional Neural Network
by: Wei Zhou, et al.
Published: (2019-01-01)