A Study of Self Distillation for Mango Image Classification

Wei Chi Chen, Wei Ta Chu

研究成果: Conference contribution

摘要

We study a knowledge transfer approach called self distillation on a mango image dataset. Taking the deepest part of a convolutional neural network as the teacher, the self distillation approach transfers the relatively richer knowledge of the deepest part to shallow parts of this network, which are viewed as the students. We verify that this approach is effective in the target mango image dataset. Furthermore, we propose two more losses to improve performance considering data characteristics. In the discussion, we not only verify effectiveness of self distillation, but also point out weakness of the current approach, which unveils potential improvement for self distillation in the future.

原文English
主出版物標題Proceedings - 2020 International Computer Symposium, ICS 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面356-359
頁數4
ISBN(電子)9781728192550
DOIs
出版狀態Published - 2020 十二月
事件2020 International Computer Symposium, ICS 2020 - Tainan, Taiwan
持續時間: 2020 十二月 172020 十二月 19

出版系列

名字Proceedings - 2020 International Computer Symposium, ICS 2020

Conference

Conference2020 International Computer Symposium, ICS 2020
國家/地區Taiwan
城市Tainan
期間20-12-1720-12-19

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 電腦科學應用
  • 資訊系統
  • 資訊系統與管理
  • 計算數學

指紋

深入研究「A Study of Self Distillation for Mango Image Classification」主題。共同形成了獨特的指紋。

引用此