Filters








676 Hits in 5.1 sec

Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation [article]

Hyungtae Lee, Heesung Kwon
2022 arXiv   pre-print
This paper introduces a self-supervised learning framework suitable for hyperspectral images that are inherently challenging to annotate.  ...  The proposed framework architecture leverages cross-domain CNN, allowing for learning representations from different hyperspectral images with varying spectral characteristics and no pixel-level annotation  ...  unlabeled hyperspectral images with different spectral properties.  ... 
arXiv:2202.03968v1 fatcat:k22cxyndi5dxdlnvdgwba4q4yu

Self-supervised Learning in Remote Sensing: A Review [article]

Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou, Xiao Xiang Zhu
2022 arXiv   pre-print
In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities.  ...  Finally, we identify a list of promising directions of future research in SSL for earth observation (SSL4EO) to pave the way for fruitful interaction of both domains.  ...  In 2019 he was a Visiting Researcher with the Cambridge Image Analysis Group (CIA), University of Cambridge, UK.  ... 
arXiv:2206.13188v1 fatcat:ibvp4ug5xbfbjkznrm6r2vycou

Unsupervised spectral sub-feature learning for hyperspectral image classification

Viktor Slavkovikj, Steven Verstockt, Wesley De Neve, Sofie Van Hoecke, Rik Van de Walle
2016 International Journal of Remote Sensing  
In this article, we propose an unsupervised feature learning method for classification of hyperspectral images.  ...  Expanded hyperspectral feature representations enable linear separation between object classes present in an image.  ...  In contrast, we learn discriminative features by mapping in an expanded but sparse feature space, which allows for linear separability of the classes present in the hyperspectral image.  ... 
doi:10.1080/01431161.2015.1125554 fatcat:ef6tvu4qi5c3vnbqnygpe3rg6a

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 6609-6622 Self-Training With Progressive Representation Enhancement for Unsupervised Cross-Domain Person Re-Identification.  ...  Li, J., +, TIP 2021 6855-6868 Self-Training With Progressive Representation Enhancement for Unsuper-vised Cross-Domain Person Re-Identification.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

2021 Index IEEE Transactions on Computational Imaging Vol. 7

2021 IEEE Transactions on Computational Imaging  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TCI 2021 864-878 Self-Supervised Learning of Monocular Depth Estimation Based on Progressive Strategy.  ...  ., +, TCI 2021 864-878 Self-Supervised Learning of Monocular Depth Estimation Based on Pro-gressive Strategy.  ... 
doi:10.1109/tci.2022.3151176 fatcat:slyirmc7c5egfjjjyfswassh24

AeroRIT: A New Scene for Hyperspectral Image Analysis [article]

Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew J. Hoffman
2020 arXiv   pre-print
To further strengthen the network, we add squeeze and excitation blocks for better channel interactions and use self-supervised learning for better encoder initialization.  ...  The full dataset, with flight lines in radiance and reflectance domain, is available for download at https://github.com/aneesh3108/AeroRIT.  ...  The former is used for improving channel inter-dependencies in the network, and the latter is used for self-supervised representation learning in some cases.  ... 
arXiv:1912.08178v3 fatcat:l75vd6kwo5e33d6pycldvie2ri

An Efficient Method for the Classification of Croplands in Scarce-Label Regions [article]

Houtan Ghaffari
2021 arXiv   pre-print
We introduce three self-supervised tasks for cropland classification.  ...  Two of the main challenges for cropland classification by satellite time-series images are insufficient ground-truth data and inaccessibility of high-quality hyperspectral images for under-developed areas  ...  Acknowledgment I would like to thank Marc Rußwurm from the Technical University of Munich for his support and fruitful discussions, which improved this work considerably.  ... 
arXiv:2103.09588v1 fatcat:erzaggmwgrabxfcwrorr4zdtdi

Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks [article]

Chaitanya Patel, Shashank Sharma, Valerie J. Pasquarella, Varun Gulshan
2022 arXiv   pre-print
Self- and semi-supervised machine learning techniques leverage unlabeled data for improving downstream task performance.  ...  We perform a rigorous evaluation of SimCLR, a self-supervised method, and FixMatch, a semi-supervised method, on three remote sensing tasks: riverbed segmentation, land cover mapping, and flood mapping  ...  ACKNOWLEDGMENTS We would like to thank Vishal Batchu for insightful discussions, Umangi Jain for reviewing our experiments, Aparna Taneja for the help in generating the Sentinel-1 unlabeled data, and Oliver  ... 
arXiv:2111.10079v2 fatcat:gzs3mu27wzfmze7octsl7ps2qy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 199-213 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ...  Li, J., +, TIP 2020 5817-5831 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Developing a machine learning framework for estimating soil moisture with VNIR hyperspectral data [article]

Sina Keller and Felix M. Riese and Johanna Stötzer and Philipp M. Maier and Stefan Hinz
2018 arXiv   pre-print
The latter are mainly supervised machine learning models. An exception are the self-organizing maps which combine unsupervised and supervised learning.  ...  In conclusion, the results of this paper provide a basis for further improvements in different research directions.  ...  Figure 1 . 1 Multiple time domain reflectometry (TDR) probes measure the An example of (a) an RGB image, (b) a hyperspectral snapshot, (c) an LWIR image in false colors.  ... 
arXiv:1804.09046v3 fatcat:frtmgrn54bhzhiwxkte75kfbre

Self-Supervised Denoising for Real Satellite Hyperspectral Imagery

Jinchun Qin, Hongrui Zhao, Bing Liu
2022 Remote Sensing  
In this paper, we propose a self-supervised learning-based algorithm, 3S-HSID, for denoising real satellite hyperspectral images without requiring external data support.  ...  With the continuous development of deep learning technology, breakthroughs have been made in improving hyperspectral image denoising algorithms based on supervised learning; however, these methods usually  ...  data, and constructed the training sample dataset needed for self-supervised learning.  ... 
doi:10.3390/rs14133083 fatcat:a6sk6sm7mvh6hc2rxuakeoawju

Deep Learning-Based Change Detection in Remote Sensing Images: A Review

Ayesha Shafique, Guo Cao, Zia Khan, Muhammad Asad, Muhammad Aslam
2022 Remote Sensing  
Therefore, this review focuses on deep learning techniques, such as supervised, unsupervised, and semi-supervised for different change detection datasets, such as SAR, multispectral, hyperspectral, VHR  ...  CD is a technique of recognizing the dissimilarities in the images acquired at distinct intervals and are used for numerous applications, such as urban area development, disaster management, land cover  ...  [182] presented a unique self-supervised learning method for CD in a bitemporal scene; they used different concepts of self-supervised learning literature, such as deep clustering, augmented view, contrastive  ... 
doi:10.3390/rs14040871 fatcat:myyprcrcyzh6fhjz5ggqdc5e54

Hyperspectral Image Classification With Contrastive Graph Convolutional Network [article]

Wentao Yu, Sheng Wan, Guangyu Li, Jian Yang, Chen Gong
2022 arXiv   pre-print
To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations  ...  Recently, Graph Convolutional Network (GCN) has been widely used in Hyperspectral Image (HSI) classification due to its satisfactory performance.  ...  Besides, one contrastive learning based method [12] termed "Self-Supervised Contrastive Learning" (SSCL) is employed for comparison.  ... 
arXiv:2205.11237v1 fatcat:3ih5erimlfdxlh46ldrhrrfe74

Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification

Lichao Mou, Xiaoqiang Lu, Xuelong Li, Xiao Xiang Zhu
2020 IEEE Transactions on Geoscience and Remote Sensing  
In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect.  ...  Hence it would be conceptually of great interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification.  ...  Illustration of nonlocal self-similarity in a hyperspectral image. For a query pixel, the ten most similar pixels in the image are plotted.  ... 
doi:10.1109/tgrs.2020.2973363 fatcat:2xt4zpifnbbzbhmpb5xcxpanoy

2019 Index IEEE Transactions on Geoscience and Remote Sensing Vol. 57

2019 IEEE Transactions on Geoscience and Remote Sensing  
., Refo-cusing and Zoom-In Polar Format Algorithm for Curvilinear Spotlight SAR Imaging on Arbitrary Region of Interest; TGRS Oct. 2019 7995-8010 Hu, T., see Kang, Z., TGRS Jan. 2019 181-193 Hu, T.,  ...  ., +, TGRS Feb. 2019 1183-1194 Self-Supervised Feature Learning With CRF Embedding for Hyperspectral Image Classification.  ...  ., +, TGRS Dec. 2019 9709-9723 Self-Supervised Feature Learning With CRF Embedding for Hyperspectral Image Classification.  ... 
doi:10.1109/tgrs.2020.2967201 fatcat:kpfxoidv5bgcfo36zfsnxe4aj4
« Previous Showing results 1 — 15 out of 676 results