TY - JOUR
T1 - AdaptMatch
T2 - Adaptive Matching for Semisupervised Binary Segmentation of Remote Sensing Images
AU - Huang, Wei
AU - Shi, Yilei
AU - Xiong, Zhitong
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - There are various binary semantic segmentation tasks in remote sensing (RS) that aim to extract the foreground areas of interest, such as buildings and roads, from the background in satellite images. In particular, semisupervised learning (SSL), which can use limited labeled data to guide a large amount of unlabeled data for model training, can significantly promote the fast applications of these tasks in practice. However, due to the predominance of the background in RS images, the foreground only accounts for a small proportion of the pixels. It poses a challenge: models are biased toward the majority class of the background, leading to poor performance on the minority class of the foreground. To address this issue, this article proposes a novel and effective SSL framework, adaptive matching (AdaptMatch), for RS binary segmentation. AdaptMatch calculates individual and adaptive thresholds of the foreground and background based on their convergence difficulty in an online manner at the training stage; the adaptive thresholds are then used to select the high-confidence pseudo-labeled data of the two classes for model self-training in turn. Extensive experiments are conducted on two widely studied RS binary segmentation tasks, building footprint extraction and road extraction, to demonstrate the effectiveness and generalizability of the proposed method. The results show that the proposed AdaptMatch achieves superior performance compared with some state-of-the-art semisupervised methods in RS binary segmentation tasks. The codes will be publicly available at https://github.com/zhu-xlab/AdaptMatch.
AB - There are various binary semantic segmentation tasks in remote sensing (RS) that aim to extract the foreground areas of interest, such as buildings and roads, from the background in satellite images. In particular, semisupervised learning (SSL), which can use limited labeled data to guide a large amount of unlabeled data for model training, can significantly promote the fast applications of these tasks in practice. However, due to the predominance of the background in RS images, the foreground only accounts for a small proportion of the pixels. It poses a challenge: models are biased toward the majority class of the background, leading to poor performance on the minority class of the foreground. To address this issue, this article proposes a novel and effective SSL framework, adaptive matching (AdaptMatch), for RS binary segmentation. AdaptMatch calculates individual and adaptive thresholds of the foreground and background based on their convergence difficulty in an online manner at the training stage; the adaptive thresholds are then used to select the high-confidence pseudo-labeled data of the two classes for model self-training in turn. Extensive experiments are conducted on two widely studied RS binary segmentation tasks, building footprint extraction and road extraction, to demonstrate the effectiveness and generalizability of the proposed method. The results show that the proposed AdaptMatch achieves superior performance compared with some state-of-the-art semisupervised methods in RS binary segmentation tasks. The codes will be publicly available at https://github.com/zhu-xlab/AdaptMatch.
KW - Adaptive threshold
KW - binary segmentation
KW - building footprint extraction
KW - remote sensing (RS)
KW - road extraction
KW - semisupervised learning (SSL)
UR - http://www.scopus.com/inward/record.url?scp=85178983896&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2023.3332490
DO - 10.1109/TGRS.2023.3332490
M3 - Article
AN - SCOPUS:85178983896
SN - 0196-2892
VL - 61
SP - 1
EP - 16
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
M1 - 5625416
ER -