VDM-DA: Virtual Domain Modeling for Source Data-Free Domain Adaptation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 6; pp. 3749 - 3760
• Main Authors: Tian, Jiayi, Zhang, Jing, Li, Wen, Xu, Dong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Alignment; Data models; Datasets; Domains; Entropy; Feature extraction; Learning; Modelling; Object recognition; Probabilistic models; source data-free; Task analysis; Three dimensional models; Three-dimensional displays; Training; Transfer learning; unsupervised domain adaptation

Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to reduce the distribution mismatch. However, access to the sour...