Filters








689 Hits in 4.3 sec

Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

Sherrie Wang, William Chen, Sang Michael Xie, George Azzari, David B. Lobell
2020 Remote Sensing  
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  ...  by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain.  ...  Related Work The growing body of research that adapts deep neural networks created for natural image segmentation to remotely sensed imagery has largely focused on two areas.  ... 
doi:10.3390/rs12020207 fatcat:k5gevpzvqjh77ikdpxr3cv5e74

Special Section Guest Editorial: Satellite Hyperspectral Remote Sensing: Algorithms and Applications

Kun Tan, Xiuping Jia, Antonio Plaza
2021 Journal of Applied Remote Sensing  
In recent years, the development of advanced computing techniques such as artificial intelligence, deep learning, and weakly supervised learning has further expanded the scope of satellite hyperspectral  ...  Deep neural networks play an important role in the field of intelligent interpretation of remote sensing data.  ...  The authors, the reviewers, and the Journal of Applied Remote Sensing production team have contributed greatly to the launch of this special section.  ... 
doi:10.1117/1.jrs.15.042601 fatcat:ksl6q5deebdv3fmgmf2b2i6wym

A Weakly-Supervised Deep Network for DSM-Aided Vehicle Detection

Xin Wu, Danfeng Hong, Jiaojiao Tian, Ralph Kiefl, Ran Tao
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
To this end, a weakly-supervised deep network (WSDN) is developed for geospatial object detection by applying a digital surface model (DSM)-aided auto-labeling and a pre-trained network learned from the  ...  With the breakthrough of the spatial resolution of optical remote sensing images at the sub-meter level and the explosive development of deep learning, geospatial object detection has achieved a growing  ...  Fig. 2 . 2 The flow chart of weakly-supervised deep network for vehicle detection. Table 1 . 1 Performance comparisons of two different methods. The best result is shown in bold.  ... 
doi:10.1109/igarss.2019.8897989 dblp:conf/igarss/WuHTK019 fatcat:26in2tfzd5dyrbb6xk7tvgnpru

Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping – Challenges and Opportunities [article]

Michael Schmitt, Jonathan Prexl, Patrick Ebel, Lukas Liebel, Xiao Xiang Zhu
2020 arXiv   pre-print
These baselines indicate that there is still a lot of potential for dedicated approaches designed to deal with remote sensing-specific forms of weak supervision.  ...  Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale  ...  Ghamisi, for making the challenge of weakly supervised learning for global land cover mapping the topic of the 2020 IEEE-GRSS Data Fusion Contest; and for numerous fruitful discussions during the design  ... 
arXiv:2002.08254v2 fatcat:4vz6isa46jbsxdqrjwtrrbglfm

WEAKLY SUPERVISED SEMANTIC SEGMENTATION OF SATELLITE IMAGES FOR LAND COVER MAPPING – CHALLENGES AND OPPORTUNITIES

M. Schmitt, J. Prexl, P. Ebel, L. Liebel, X. X. Zhu
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
These baselines indicate that there is still a lot of potential for dedicated approaches designed to deal with remote sensing-specific forms of weak supervision.  ...  Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale  ...  Ghamisi, for making the challenge of weakly supervised learning for global land cover mapping the topic of the 2020 IEEE-GRSS Data Fusion Contest; and for numerous fruitful discussions during the design  ... 
doi:10.5194/isprs-annals-v-3-2020-795-2020 fatcat:zmaqvbtsobfpbd55llrka5lvem

Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training

Qingyu Li, Yilei Shi, Xiao Xiang Zhu
2022 IEEE Transactions on Geoscience and Remote Sensing  
Results of Different Semantic Segmentation Networks for Supervised Learning The comparisons among different semantic segmentation networks for supervised learning are presented in this section.  ...  Weakly-supervised training-based methods [37] [38] [39] [40] integrate weakly-supervised learning in their approaches.  ... 
doi:10.1109/tgrs.2022.3174636 fatcat:a3micpylhvhntkrhwijawy42fm

Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

Yanbing Bai, Wenqi Wu, Zhengxin Yang, Jinze Yu, Bo Zhao, Xing Liu, Hanfang Yang, Erick Mas, Shunichi Koshimura
2021 Remote Sensing  
flood disaster events from only post-flood remote sensing imageries still remains challenging.  ...  initially due to the lack of large-scale labelled remote sensing images of flood events.  ...  We also thank the Core Research Cluster of Disaster Science at Tohoku University (a Designated National University) for their support.  ... 
doi:10.3390/rs13112220 fatcat:4mrb5eyitvgslir743tynhixcy

Weakly Labeling the Antarctic: The Penguin Colony Case [article]

Hieu Le, Bento Gonçalves, Dimitris Samaras, Heather Lynch
2019 arXiv   pre-print
In this work, we present a deep learning based model for semantic segmentation of Ad\'elie penguin colonies in high-resolution satellite imagery.  ...  In the face of a scarcity of pixel-level annotation masks, we propose a weakly-supervised framework to effectively learn a segmentation model from weak labels.  ...  Weakly-Supervised Learning Framework For Penguin Colony Segmentation.  ... 
arXiv:1905.03313v2 fatcat:zfrayqjjgzgxbbxq65c5itohpm

Semi-Supervised Remote Sensing Image Semantic Segmentation via Consistency Regularization and Average Update of Pseudo-Label

Jiaxin Wang, Chris H. Q. Ding, Sibao Chen, Chenggang He, Bin Luo
2020 Remote Sensing  
This paper proposes a method for remote sensing image segmentation based on semi-supervised learning.  ...  To solve this problem, we explore semi-supervised learning methods and appropriately utilize a large amount of unlabeled data to improve the performance of remote sensing image segmentation.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs12213603 fatcat:jtg6jxaebvebpm35yunq5idziq

Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images [article]

Yao Wei, Shunping Ji
2020 arXiv   pre-print
Road surface extraction from remote sensing images using deep learning methods has achieved good performance, while most of the existing methods are based on fully supervised learning, which requires a  ...  weakly supervised methods at least 4%.  ...  The main contributions of our research are as follows. 1) We propose a novel scribble-based weakly supervised deep learning approach (called ScRoadExtractor) for road surface extraction from remote sensing  ... 
arXiv:2010.13106v1 fatcat:o5qn53rzwfcotphkcxithbgpdm

SPATIAL RESOLUTION ENHANCEMENT OF LAND COVER MAPPING USING DEEP CONVOLUTIONAL NETS

Q. Yu, W. Liu, J. Li
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
This paper proposes a novel spatiotemporal fusion method based on deep convolutional neural networks under the application background of massive remote sensing data, as well as the large spatial resolution  ...  Multispectral satellite imagery is the primary data source for monitoring land cover change and characterizing land cover at the global scale.  ...  Therefore, deep learning-based land cover classification has become a current hotpot in the remote sensing research community.  ... 
doi:10.5194/isprs-archives-xliii-b1-2020-85-2020 fatcat:hvcnarzk5ra7nhv225qilfd7v4

Weakly Supervised Object Localization and Detection: A Survey [article]

Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
2021 arXiv   pre-print
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems  ...  applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.  ...  Remote Sensing Imagery Analysis Remote sensing imagery analysis is one of the most widely studied applications based on weakly supervised object localization and detection, where the input images are usually  ... 
arXiv:2104.07918v1 fatcat:dwl6sjfzibdilnvjnrbifp4uke

Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery [article]

Zhuo Zheng, Ailong Ma, Liangpei Zhang, Yanfei Zhong
2021 arXiv   pre-print
For high spatial resolution (HSR) remote sensing images, bitemporal supervised learning always dominates change detection using many pairwise labeled bitemporal images.  ...  In this paper, we propose single-temporal supervised learning (STAR) for change detection from a new perspective of exploiting object changes in unpaired images as supervisory signals.  ...  Introduction Object change detection using multi-temporal high spatial resolution (HSR) remote sensing imagery is a meaningful but challenging fundamental task in remote sensing and earth vision, which  ... 
arXiv:2108.07002v1 fatcat:y6axqfzqg5gjpbtc3ytbq6oaay

Interactive Learning for Semantic Segmentation in Earth Observation [article]

Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux, Guy Le Besnerais
2020 arXiv   pre-print
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding.  ...  Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation).  ...  State of the art Weakly supervised learning aims at making algorithms learn on data with flawed or partial labels.  ... 
arXiv:2009.11250v1 fatcat:mqgilrntqvdgjba7biboulryni

Road Extraction from Very High Resolution Images Using Weakly labeled OpenStreetMap Centerline

Songbing Wu, Chun Du, Hao Chen, Yingxiao Xu, Ning Guo, Ning Jing
2019 ISPRS International Journal of Geo-Information  
Due to the success of semantic segmentation based on deep learning in the application of computer vision, extracting road networks from VHR (Very High Resolution) imagery becomes a method of updating geographic  ...  The major shortcoming of deep learning methods for road networks extraction is that they need a massive amount of high quality pixel-wise training datasets, which is hard to obtain.  ...  The authors also thanks Ruize Shao for helping labeled some images and Ye Wu ptovided the original Google satellite images. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijgi8110478 fatcat:ji6wqnk4arh3liugukvz6x3sqa
« Previous Showing results 1 — 15 out of 689 results