Yan Li, Tai-Kang Tian, Meng-Yu Zhuang, Yu-Ting Sun. De-biased knowledge distillation framework based on knowledge infusion and label de-biasing techniques[J]. Journal of Electronic Science and Technology, 2024, 22(3): 100278
- Journal of Electronic Science and Technology
- Vol. 22, Issue 3, 100278 (2024)
Fig. 1. Illustration of the classical knowledge distillation (KD) and our de-biased knowledge distillation (DeBKD).
Fig. 2. Workflow of the proposed de-biased knowledge distillation framework.
Fig. 3. Process of knowledge infusion.
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 1. Comparison of distillation effects across different datasets.
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 2. Impact of different learning freedom on the classification accuracy.
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 3. Impact of knowledge infusion (KI) on model performance (Δ indicates the change in performance).
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20