Center transfer for supervised domain adaptation
Yükleniyor...
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Domain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature's discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.
Açıklama
Anahtar Kelimeler
Supervised Domain Adaptation, Deep Learning, Center Transfer Loss, Transfer Learning
Kaynak
Applied Intelligence
WoS Q Değeri
Q2
Scopus Q Değeri
Cilt
Sayı
Künye
Huang, X., Zhou, N., Huang, J., Zhang, H., Pedrycz, W., & Choi, K. S. (2023). Center transfer for supervised domain adaptation. Applied Intelligence, 1-17.
