TY - GEN
T1 - Contrastive Adaptive Segmentation Method for Spartina Alterniflora Based on Intermediate Domain Prototypes
AU - Zhao, Boyu
AU - Li, Zhengmao
AU - Jiang, Xiangyang
AU - Zhang, Mengmeng
AU - Li, Wei
AU - Zhang, Yuxiang
AU - Song, Xiukai
N1 - Publisher Copyright:
© 2024 ACM.
PY - 2024/1/19
Y1 - 2024/1/19
N2 - Observing spartina alterniflora (S.alterniflora) with multi-temporal remote sensing data aids in comprehending its development and spread in wetland ecosystems, thereby facilitating the formulation of effective strategies for its containment and control. Unsupervised Domain Adaptation (UDA) techniques uncover its spatio-temporal patterns, but most methods miss critical domain and class differences, whereas Intermediate Domain Prototype Class-level Learning Network (IDCNet) addresses these gaps. IDCNet generates class prototypes based on intermediate domain features, incorporating inter-class information for more accurate distribution alignment. Experimental results on two cross-year multi-spectral datasets demonstrate that the proposed IDCNet outperforms several state-of-the-art UDA methods.
AB - Observing spartina alterniflora (S.alterniflora) with multi-temporal remote sensing data aids in comprehending its development and spread in wetland ecosystems, thereby facilitating the formulation of effective strategies for its containment and control. Unsupervised Domain Adaptation (UDA) techniques uncover its spatio-temporal patterns, but most methods miss critical domain and class differences, whereas Intermediate Domain Prototype Class-level Learning Network (IDCNet) addresses these gaps. IDCNet generates class prototypes based on intermediate domain features, incorporating inter-class information for more accurate distribution alignment. Experimental results on two cross-year multi-spectral datasets demonstrate that the proposed IDCNet outperforms several state-of-the-art UDA methods.
KW - Intermediate Domain Prototypical Contrast Adaptation
KW - Multitemporal Remote Sensing Image Segmentation
KW - Spartina Alterniflora
KW - Unsupervised Domain Adaptation
UR - https://www.scopus.com/pages/publications/85192763019
U2 - 10.1145/3647649.3647663
DO - 10.1145/3647649.3647663
M3 - Conference contribution
AN - SCOPUS:85192763019
T3 - ACM International Conference Proceeding Series
SP - 85
EP - 91
BT - ICIGP 2024 - Proceedings of the 2024 7th International Conference on Image and Graphics Processing
PB - Association for Computing Machinery
T2 - 7th International Conference on Image and Graphics Processing, ICIGP 2024
Y2 - 19 January 2024 through 21 January 2024
ER -
