Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast
View/ Open
Impact
Scholar |
Other documents of the author: kang, jian; Fernandez-Beltran, Ruben; Duan, Puhong; Liu, Sicong; Plaza, Antonio
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum ContrastDate
2020-07-14Publisher
IEEEBibliographic citation
KANG, Jian, et al. Deep unsupervised embedding for remotely sensed images based on spatially augmented momentum contrast. IEEE Transactions on Geoscience and Remote Sensing, 2020.Type
info:eu-repo/semantics/articlePublisher version
https://ieeexplore.ieee.org/document/9140372Version
info:eu-repo/semantics/publishedVersionSubject
Abstract
Convolutional neural networks (CNNs) have achieved great success when characterizing remote sensing (RS) images. However, the lack of sufficient annotated data (together with the high complexity of the RS image domain) ... [+]
Convolutional neural networks (CNNs) have achieved great success when characterizing remote sensing (RS) images. However, the lack of sufficient annotated data (together with the high complexity of the RS image domain) often makes supervised and transfer learning schemes limited from an operational perspective. Despite the fact that unsupervised methods can potentially relieve these limitations, they are frequently unable to effectively exploit relevant prior knowledge about the RS domain, which may eventually constrain their final performance. In order to address these challenges, this article presents a new unsupervised deep metric learning model, called spatially augmented momentum contrast (SauMoCo), which has been specially designed to characterize unlabeled RS scenes. Based on the first law of geography, the proposed approach defines spatial augmentation criteria to uncover semantic relationships among land cover tiles. Then, a queue of deep embeddings is constructed to enhance the semantic variety of RS tiles within the considered contrastive learning process, where an auxiliary CNN model serves as an updating mechanism. Our experimental comparison, including different state-of-the-art techniques and benchmark RS image archives, reveals that the proposed approach obtains remarkable performance gains when characterizing unlabeled scenes since it is able to substantially enhance the discrimination ability among complex land cover categories. The source codes of this article will be made available to the RS community for reproducible research. [-]
Investigation project
Grant Number 2018YFB 050500; RTI2018-098651-B-C54; Ref. GR18060; H2020 EOXPOSURE project (No. 734541)Rights
http://rightsstatements.org/vocab/CNE/1.0/
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- INIT_Articles [754]