Dynamic Label Smoothing for Fine-Grained Dataset
- Title
- Dynamic Label Smoothing for Fine-Grained Dataset
- Authors
- 이동구
- Date Issued
- 2022
- Publisher
- 포항공과대학교
- Abstract
- This paper addresses the classification task of deep learning model. We provide a proposed method to improve Label Smoothing based regularization technique between loss and data. We mathematically show that label smoothing performs poorly on fine-grained data. Based on mathematical evidence, we propose Dynamic Label Smoothing, a new Label Smoothing based on regularization between loss and data. Experimental results show that Dynamic Label Smoothing provides more accurate visualization than the previous research.
- URI
- http://postech.dcollection.net/common/orgView/200000637933
https://oasis.postech.ac.kr/handle/2014.oak/117418
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.