{"title":"Handling session mismatch by fusion-based co-training: An empirical study using face and speech multimodal biometrics","authors":"N. Poh, J. Kittler, A. Rattani","doi":"10.1109/CIBIM.2014.7015447","DOIUrl":null,"url":null,"abstract":"Semi-supervised learning has been shown to be a viable training strategy for handling the mismatch between training and test samples. For multimodal biometric systems, classical semi-supervised learning strategies such as self-training and co-training may not have fully exploited the advantage of a multimodal fusion, notably due to the fusion module. For this reason, we explore a novel semi-supervised training strategy known as fusion-based co-training that generalizes the classical co-training such that it can use a trainable fusion classifier. Our experiments on the BANCA face and speech database show that this proposed strategy is a viable approach. In addition, we also address the resolved issue of how to select the decision threshold for adaptation. In particular, we find that a strong classifier, including a multimodal system, may benefit better from a more relaxed threshold whereas a weak classifier may benefit better from a more stringent one.","PeriodicalId":432938,"journal":{"name":"2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIBIM.2014.7015447","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
Semi-supervised learning has been shown to be a viable training strategy for handling the mismatch between training and test samples. For multimodal biometric systems, classical semi-supervised learning strategies such as self-training and co-training may not have fully exploited the advantage of a multimodal fusion, notably due to the fusion module. For this reason, we explore a novel semi-supervised training strategy known as fusion-based co-training that generalizes the classical co-training such that it can use a trainable fusion classifier. Our experiments on the BANCA face and speech database show that this proposed strategy is a viable approach. In addition, we also address the resolved issue of how to select the decision threshold for adaptation. In particular, we find that a strong classifier, including a multimodal system, may benefit better from a more relaxed threshold whereas a weak classifier may benefit better from a more stringent one.