TY - GEN
T1 - Generative Alignment of Posterior Probabilities for Source-free Domain Adaptation
AU - Chhabra, Sachin
AU - Venkateswara, Hemanth
AU - Li, Baoxin
N1 - Funding Information:
The work was supported in part by a grant from ONR. Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR.
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Existing domain adaptation literature comprises multiple techniques that align the labeled source and unlabeled target domains at different stages, and predict the target labels. In a source-free domain adaptation setting, the source data is not available for alignment. We present a source-free generative paradigm that captures the relations between the source categories and enforces them onto the unlabeled target data, thereby circumventing the need for source data without introducing any new hyper-parameters. The adaptation is performed through the adversarial alignment of the posterior probabilities of the source and target categories. The proposed approach demonstrates competitive performance against other source-free domain adaptation techniques and can also be used for source-present settings.
AB - Existing domain adaptation literature comprises multiple techniques that align the labeled source and unlabeled target domains at different stages, and predict the target labels. In a source-free domain adaptation setting, the source data is not available for alignment. We present a source-free generative paradigm that captures the relations between the source categories and enforces them onto the unlabeled target data, thereby circumventing the need for source data without introducing any new hyper-parameters. The adaptation is performed through the adversarial alignment of the posterior probabilities of the source and target categories. The proposed approach demonstrates competitive performance against other source-free domain adaptation techniques and can also be used for source-present settings.
KW - Algorithms: Machine learning architectures
KW - and algorithms (including transfer)
KW - formulations
UR - http://www.scopus.com/inward/record.url?scp=85149012728&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149012728&partnerID=8YFLogxK
U2 - 10.1109/WACV56688.2023.00411
DO - 10.1109/WACV56688.2023.00411
M3 - Conference contribution
AN - SCOPUS:85149012728
T3 - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
SP - 4114
EP - 4123
BT - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Y2 - 3 January 2023 through 7 January 2023
ER -