TY - JOUR
T1 - Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image Classification
AU - Zhang, Yuxiang
AU - Li, Wei
AU - Zhang, Mengmeng
AU - Wang, Shuai
AU - Tao, Ran
AU - Du, Qian
N1 - Publisher Copyright:
© 2012 IEEE.
PY - 2024/2/1
Y1 - 2024/2/1
N2 - Most domain adaptation (DA) methods in cross-scene hyperspectral image classification focus on cases where source data (SD) and target data (TD) with the same classes are obtained by the same sensor. However, the classification performance is significantly reduced when there are new classes in TD. In addition, domain alignment, as one of the main approaches in DA, is carried out based on local spatial information, rarely taking into account nonlocal spatial information (nonlocal relationships) with strong correspondence. A graph information aggregation cross-domain few-shot learning (Gia-CFSL) framework is proposed, intending to make up for the above-mentioned shortcomings by combining FSL with domain alignment based on graph information aggregation. SD with all label samples and TD with a few label samples are implemented for FSL episodic training. Meanwhile, intradomain distribution extraction block (IDE-block) and cross-domain similarity aware block (CSA-block) are designed. The IDE-block is used to characterize and aggregate the intradomain nonlocal relationships and the interdomain feature and distribution similarities are captured in the CSA-block. Furthermore, feature-level and distribution-level cross-domain graph alignments are used to mitigate the impact of domain shift on FSL. Experimental results on three public HSI datasets demonstrate the superiority of the proposed method. The codes will be available from the website: https://github.com/YuxiangZhang-BIT/IEEE_TNNLS_Gia-CFSL.
AB - Most domain adaptation (DA) methods in cross-scene hyperspectral image classification focus on cases where source data (SD) and target data (TD) with the same classes are obtained by the same sensor. However, the classification performance is significantly reduced when there are new classes in TD. In addition, domain alignment, as one of the main approaches in DA, is carried out based on local spatial information, rarely taking into account nonlocal spatial information (nonlocal relationships) with strong correspondence. A graph information aggregation cross-domain few-shot learning (Gia-CFSL) framework is proposed, intending to make up for the above-mentioned shortcomings by combining FSL with domain alignment based on graph information aggregation. SD with all label samples and TD with a few label samples are implemented for FSL episodic training. Meanwhile, intradomain distribution extraction block (IDE-block) and cross-domain similarity aware block (CSA-block) are designed. The IDE-block is used to characterize and aggregate the intradomain nonlocal relationships and the interdomain feature and distribution similarities are captured in the CSA-block. Furthermore, feature-level and distribution-level cross-domain graph alignments are used to mitigate the impact of domain shift on FSL. Experimental results on three public HSI datasets demonstrate the superiority of the proposed method. The codes will be available from the website: https://github.com/YuxiangZhang-BIT/IEEE_TNNLS_Gia-CFSL.
KW - Cross-scene
KW - distribution alignment
KW - domain adaption
KW - few-shot learning (FSL)
KW - graph neural network (GNN)
KW - hyperspectral image classification
UR - http://www.scopus.com/inward/record.url?scp=85133790632&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2022.3185795
DO - 10.1109/TNNLS.2022.3185795
M3 - Article
C2 - 35771788
AN - SCOPUS:85133790632
SN - 2162-237X
VL - 35
SP - 1912
EP - 1925
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 2
ER -