TY - GEN
T1 - Source-Free Domain Adaptation for Cross-Scene Hyperspectral Image Classification
AU - Xu, Zun
AU - Wei, Wei
AU - Zhang, Lei
AU - Nie, Jiangtao
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Deep learning based cross-domain hyperspectral image (HSI) classification methods were proposed to train a classifier adapted to unlabeled target domain with the help of abundant labeled data in source domain. Although the existing methods show their potential for cross-domain HSI classification, the data in source domain may not be provided due to the data privacy, which limits the availability of these methods. In this case, how to utilize the model or knowledge trained from source domain becomes a more challenging problem. In this study, we emphasize on this problem, and propose source-free unsupervised domain adaptation method for HSI classification. Specifically, we firstly design a source domain HSI spectral feature generator, and then realize the class-wised alignment between the generated source domain HSI spectral features and the target domain features of HSI through contrastive learning. To solve the dilemma of without labels in the target domain, we also utilize a logits-weighted prototype classifier to iteratively obtain the data label of the target domain. Experiments on two cross-scene HSI datasets demonstrate the effectiveness of the proposed method when only providing the model trained from the source domain.
AB - Deep learning based cross-domain hyperspectral image (HSI) classification methods were proposed to train a classifier adapted to unlabeled target domain with the help of abundant labeled data in source domain. Although the existing methods show their potential for cross-domain HSI classification, the data in source domain may not be provided due to the data privacy, which limits the availability of these methods. In this case, how to utilize the model or knowledge trained from source domain becomes a more challenging problem. In this study, we emphasize on this problem, and propose source-free unsupervised domain adaptation method for HSI classification. Specifically, we firstly design a source domain HSI spectral feature generator, and then realize the class-wised alignment between the generated source domain HSI spectral features and the target domain features of HSI through contrastive learning. To solve the dilemma of without labels in the target domain, we also utilize a logits-weighted prototype classifier to iteratively obtain the data label of the target domain. Experiments on two cross-scene HSI datasets demonstrate the effectiveness of the proposed method when only providing the model trained from the source domain.
KW - contrastive learning
KW - HSI classification
KW - source-free
KW - Unsupervised Domain Adaptation
UR - http://www.scopus.com/inward/record.url?scp=85140367072&partnerID=8YFLogxK
U2 - 10.1109/IGARSS46834.2022.9883053
DO - 10.1109/IGARSS46834.2022.9883053
M3 - 会议稿件
AN - SCOPUS:85140367072
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 3576
EP - 3579
BT - IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Y2 - 17 July 2022 through 22 July 2022
ER -