Eikd: method of extracting important information from feature map for knowledge distillation
- 23 June 2025
- journal article
- research article
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- p. 1-14
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61976098, 61976098, 61976098, 61976098, 61976098, 61976098)
- Natural Science Foundation for Outstanding Young Scholars of Fujian Province (61976098, 61976098, 61976098, 61976098, 61976098, 61976098)
- High-level Talent Innovation and Entrepreneurship Project of Quanzhou City (2023C013R, 2023C013R, 2023C013R, 2023C013R, 2023C013R, 2023C013R)
This publication has 25 references indexed in Scilit:
- Ability-aware knowledge distillation for resource-constrained embedded devicesJournal of Systems Architecture, 2023
- Improving knowledge distillation via pseudo-multi-teacher networkMachine Vision and Applications, 2023
- Prune Your Model Before Distill It2022
- Learning Metrics From Teachers: Compact Networks for Image Embedding2019
- Relational Knowledge Distillation2019
- Learning Deep Representations with Probabilistic Knowledge Transfer2018
- A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015