Next Article in Journal
Pollution Trends in China from 2000 to 2017: A Multi-Sensor View from Space
Previous Article in Journal
Correction: Wang, L., et al. Assessment of the Dual Polarimetric Sentinel-1A Data for Forest Fuel Moisture Content Estimation. Remote Sensing 2019, 11(13), 1568
Open AccessArticle

Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

1
Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA 94305, USA
2
Department of Earth System Science, Stanford University, Stanford, CA 94305, USA
3
Department of Computer Science, Stanford University, Stanford, CA 94305, USA
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(2), 207; https://doi.org/10.3390/rs12020207
Received: 5 November 2019 / Revised: 10 December 2019 / Accepted: 29 December 2019 / Published: 7 January 2020
(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful translation to remote sensing tasks has been limited by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain. In this work, we perform cropland segmentation using two types of labels commonly found in remote sensing datasets that can be considered sources of “weak supervision”: (1) labels comprised of single geotagged points and (2) image-level labels. We demonstrate that (1) a U-Net trained on a single labeled pixel per image and (2) a U-Net image classifier transferred to segmentation can outperform pixel-level algorithms such as logistic regression, support vector machine, and random forest. While the high performance of neural networks is well-established for large datasets, our experiments indicate that U-Nets trained on weak labels outperform baseline methods with as few as 100 labels. Neural networks, therefore, can combine superior classification performance with efficient label usage, and allow pixel-level labels to be obtained from image labels. View Full-Text
Keywords: deep learning; image segmentation; weak supervision; agriculture; Landsat; land cover classification deep learning; image segmentation; weak supervision; agriculture; Landsat; land cover classification
Show Figures

Figure 1

MDPI and ACS Style

Wang, S.; Chen, W.; Xie, S.M.; Azzari, G.; Lobell, D.B. Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery. Remote Sens. 2020, 12, 207.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop