JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Voting and Ensemble Schemes Based on CNN Models for Photo-Based Gender Prediction |
| 영문제목(English Title) |
Voting and Ensemble Schemes Based on CNN Models for Photo-Based Gender Prediction |
| 저자(Author) |
Kyoungson Jhang
|
| 원문수록처(Citation) |
VOL 16 NO. 04 PP. 0809 ~ 0819 (2020. 08) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Gender prediction accuracy increases as convolutional neural network (CNN) architecture evolves. This paper compares voting and ensemble schemes to utilize the already trained five CNN models to further improve gender prediction accuracy. The majority voting usually requires odd-numbered models while the proposed softmax-based voting can utilize any number of models to improve accuracy. The ensemble of CNN models combined with one more fully-connected layer requires further tuning or training of the models combined. With experiments, it is observed that the voting or ensemble of CNN models leads to further improvement of gender prediction accuracy and that especially softmax-based voters always show better gender prediction accuracy than majority voters. Also, compared with softmax-based voters, ensemble models show a slightly better or similar accuracy with added training of the combined CNN models. Softmax-based voting can be a fast and efficient way to get better accuracy without further training since the selection of the top accuracy models among available CNN pre-trained models usually leads to similar accuracy to that of the corresponding ensemble models.
|
| 키워드(Keyword) |
Majority Voting
Softmax-based Voting
Ensemble Scheme
Gender Prediction
CNN models
|
| 파일첨부 |
PDF 다운로드
|
