PiCoCo: Pixelwise Contrast and Consistency Learning for Semisupervised Building Footprint Segmentation
![Thumbnail](/xmlui/bitstream/handle/10234/196138/PiCoCo_2021_IEEE.pdf.jpg?sequence=4&isAllowed=y)
Ver/ Abrir
Impacto
![Google Scholar](/xmlui/themes/Mirage2/images/uji/logo_google.png)
![Microsoft Academico](/xmlui/themes/Mirage2/images/uji/logo_microsoft.png)
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadatos
Título
PiCoCo: Pixelwise Contrast and Consistency Learning for Semisupervised Building Footprint SegmentationFecha de publicación
2021-10-11Editor
IEEEISSN
1939-1404; 2151-1535Cita bibliográfica
J. Kang, Z. Wang, R. Zhu, X. Sun, R. Fernandez-Beltran and A. Plaza, "PiCoCo: Pixelwise Contrast and Consistency Learning for Semisupervised Building Footprint Segmentation," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 10548-10559, 2021, doi: 10.1109/JSTARS.2021.3119286.Tipo de documento
info:eu-repo/semantics/articleVersión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
Building footprint segmentation from high-resolution
remote sensing (RS) images plays a vital role in urban planning, disaster response, and population density estimation. Convolutional
neural networks (CNNs) have ... [+]
Building footprint segmentation from high-resolution
remote sensing (RS) images plays a vital role in urban planning, disaster response, and population density estimation. Convolutional
neural networks (CNNs) have been recently used as a workhorse for
effectively generating building footprints. However, to completely
exploit the prediction power of CNNs, large-scale pixel-level annotations are required. Most state-of-the-art methods based on CNNs
are focused on the design of network architectures for improving
the predictions of building footprints with full annotations, while
few works have been done on building footprint segmentation with
limited annotations. In this article, we propose a novel semisupervised learning method for building footprint segmentation, which
can effectively predict building footprints based on the network
trained with few annotations (e.g., only 0.0324 km2 out of 2.25-km2
area is labeled). The proposed method is based on investigating
the contrast between the building and background pixels in latent
space and the consistency of predictions obtained from the CNN
models when the input RS images are perturbed. Thus, we term the
proposed semisupervised learning framework of building footprint segmentation as PiCoCo, which is based on the enforcement of
Pixelwise Contrast and Consistency during the learning phase. Our
experiments, conducted on two benchmark building segmentation
datasets, validate the effectiveness of our proposed framework as
compared to several state-of-the-art building footprint extraction
and semisupervised semantic segmentation methods. [-]
Publicado en
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 14 (2021)Entidad financiadora
Jiangsu Province Science Foundation for Youths | National Natural Science Foundation of China | Jiangsu Higher Education Institution | Ministerio de Ciencia, Innovación y Universidades (España) | APRISA | Generalitat Valenciana | FEDER-Junta de Extremadura | European Union
Código del proyecto o subvención
BK20210707 | 62101371 | 62076241 | RTI2018-098651-B-C54 | PID2019- 110315RB-I00 | GV/2020/167 | GR18060 | info:eu-repo/grantAgreement/EC/H2020/734541
Derechos de acceso
info:eu-repo/semantics/openAccess
Aparece en las colecciones
- INIT_Articles [751]