KCC 2021
Current Result Document :
| 한글제목(Korean Title) |
의료영상 분류를 위한 거리기반 메트릭 손실의 비교 |
| 영문제목(English Title) |
Comparison of Distance-Based Metric Losses for Medical Image Classification |
| 저자(Author) |
기미르 러만
이상웅
Raman Ghimire
Sang-Woong Lee
|
| 원문수록처(Citation) |
VOL 48 NO. 01 PP. 0657 ~ 0658 (2021. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Distance metric learning has been used as an effective strategy to learn intrinsic pattern of the image datasets across various computer vision domain. In this paper, we compare 3 different types of loss functions: pair-based loss (Triplet loss, Soft-Triple loss) and proxy-based loss (Proxy-NCA, Proxy-Anchor) in a multi-class classification task. We have used resnet-50 as network architecture and our result shows that Proxy-Anchor loss achieved 93.44% mean average precision on average compared to the Triplet loss, SoftTriple Loss and Proxy-NCA loss which achieved 92.53%, 93.63% and 91.98% respectively. |
| 키워드(Keyword) |
Medical Image Classification
Triplet Loss
Soft-Triple Loss
Proxy-NCA Loss
Proxy-Anchor Loss
|
| 파일첨부 |
PDF 다운로드
|
