Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment
Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually require a large number samples for tasks such as classification,...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Pande, Shivam Braham, Nassim Ait Ali Wang, Yi Albrecht, Conrad M Banerjee, Biplab Zhu, Xiao Xiang |
description | Hyperspectral image (HSI) classification is gaining a lot of momentum in
present time because of high inherent spectral information within the images.
However, these images suffer from the problem of curse of dimensionality and
usually require a large number samples for tasks such as classification,
especially in supervised setting. Recently, to effectively train the deep
learning models with minimal labelled samples, the unlabeled samples are also
being leveraged in self-supervised and semi-supervised setting. In this work,
we leverage the idea of semi-supervised learning to assist the discriminative
self-supervised pretraining of the models. The proposed method takes different
augmented views of the unlabeled samples as input and assigns them the same
pseudo-label corresponding to the labelled sample from the downstream task. We
train our model on two HSI datasets, namely Houston dataset (from data fusion
contest, 2013) and Pavia university dataset, and show that the proposed
approach performs better than self-supervised approach and supervised training. |
doi_str_mv | 10.48550/arxiv.2306.10955 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2306_10955</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2306_10955</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-d9c15cb73e9654874dbc2607d220f822e0bc12ea552fcd682c3345e1421962f73</originalsourceid><addsrcrecordid>eNotj8tugzAURL3pokr7AV3FPwC1r7GBZRX1JUXqItmji32hlsBBNqXl75ukXY000hzNYexBiryotBaPGH_8koMSJpei1vqWtQcafXb4miguPpHje8IYfOh5d4r8cz33aSI7Rxy4H7GnxNuVh1PgE0YcaY7e4jCsfIrkvJ0vy8XTN8eUfB9GCvMdu-lwSHT_nxt2fHk-7t6y_cfr--5pn6EpdeZqK7VtS0W10UVVFq61YETpAERXAZBorQRCraGzzlRglSo0yQJkbaAr1YZt_7BXyWaK57txbS6yzVVW_QJ_PFEL</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment</title><source>arXiv.org</source><creator>Pande, Shivam ; Braham, Nassim Ait Ali ; Wang, Yi ; Albrecht, Conrad M ; Banerjee, Biplab ; Zhu, Xiao Xiang</creator><creatorcontrib>Pande, Shivam ; Braham, Nassim Ait Ali ; Wang, Yi ; Albrecht, Conrad M ; Banerjee, Biplab ; Zhu, Xiao Xiang</creatorcontrib><description>Hyperspectral image (HSI) classification is gaining a lot of momentum in
present time because of high inherent spectral information within the images.
However, these images suffer from the problem of curse of dimensionality and
usually require a large number samples for tasks such as classification,
especially in supervised setting. Recently, to effectively train the deep
learning models with minimal labelled samples, the unlabeled samples are also
being leveraged in self-supervised and semi-supervised setting. In this work,
we leverage the idea of semi-supervised learning to assist the discriminative
self-supervised pretraining of the models. The proposed method takes different
augmented views of the unlabeled samples as input and assigns them the same
pseudo-label corresponding to the labelled sample from the downstream task. We
train our model on two HSI datasets, namely Houston dataset (from data fusion
contest, 2013) and Pavia university dataset, and show that the proposed
approach performs better than self-supervised approach and supervised training.</description><identifier>DOI: 10.48550/arxiv.2306.10955</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-06</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2306.10955$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2306.10955$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pande, Shivam</creatorcontrib><creatorcontrib>Braham, Nassim Ait Ali</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Albrecht, Conrad M</creatorcontrib><creatorcontrib>Banerjee, Biplab</creatorcontrib><creatorcontrib>Zhu, Xiao Xiang</creatorcontrib><title>Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment</title><description>Hyperspectral image (HSI) classification is gaining a lot of momentum in
present time because of high inherent spectral information within the images.
However, these images suffer from the problem of curse of dimensionality and
usually require a large number samples for tasks such as classification,
especially in supervised setting. Recently, to effectively train the deep
learning models with minimal labelled samples, the unlabeled samples are also
being leveraged in self-supervised and semi-supervised setting. In this work,
we leverage the idea of semi-supervised learning to assist the discriminative
self-supervised pretraining of the models. The proposed method takes different
augmented views of the unlabeled samples as input and assigns them the same
pseudo-label corresponding to the labelled sample from the downstream task. We
train our model on two HSI datasets, namely Houston dataset (from data fusion
contest, 2013) and Pavia university dataset, and show that the proposed
approach performs better than self-supervised approach and supervised training.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tugzAURL3pokr7AV3FPwC1r7GBZRX1JUXqItmji32hlsBBNqXl75ukXY000hzNYexBiryotBaPGH_8koMSJpei1vqWtQcafXb4miguPpHje8IYfOh5d4r8cz33aSI7Rxy4H7GnxNuVh1PgE0YcaY7e4jCsfIrkvJ0vy8XTN8eUfB9GCvMdu-lwSHT_nxt2fHk-7t6y_cfr--5pn6EpdeZqK7VtS0W10UVVFq61YETpAERXAZBorQRCraGzzlRglSo0yQJkbaAr1YZt_7BXyWaK57txbS6yzVVW_QJ_PFEL</recordid><startdate>20230619</startdate><enddate>20230619</enddate><creator>Pande, Shivam</creator><creator>Braham, Nassim Ait Ali</creator><creator>Wang, Yi</creator><creator>Albrecht, Conrad M</creator><creator>Banerjee, Biplab</creator><creator>Zhu, Xiao Xiang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230619</creationdate><title>Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment</title><author>Pande, Shivam ; Braham, Nassim Ait Ali ; Wang, Yi ; Albrecht, Conrad M ; Banerjee, Biplab ; Zhu, Xiao Xiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-d9c15cb73e9654874dbc2607d220f822e0bc12ea552fcd682c3345e1421962f73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Pande, Shivam</creatorcontrib><creatorcontrib>Braham, Nassim Ait Ali</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Albrecht, Conrad M</creatorcontrib><creatorcontrib>Banerjee, Biplab</creatorcontrib><creatorcontrib>Zhu, Xiao Xiang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pande, Shivam</au><au>Braham, Nassim Ait Ali</au><au>Wang, Yi</au><au>Albrecht, Conrad M</au><au>Banerjee, Biplab</au><au>Zhu, Xiao Xiang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment</atitle><date>2023-06-19</date><risdate>2023</risdate><abstract>Hyperspectral image (HSI) classification is gaining a lot of momentum in
present time because of high inherent spectral information within the images.
However, these images suffer from the problem of curse of dimensionality and
usually require a large number samples for tasks such as classification,
especially in supervised setting. Recently, to effectively train the deep
learning models with minimal labelled samples, the unlabeled samples are also
being leveraged in self-supervised and semi-supervised setting. In this work,
we leverage the idea of semi-supervised learning to assist the discriminative
self-supervised pretraining of the models. The proposed method takes different
augmented views of the unlabeled samples as input and assigns them the same
pseudo-label corresponding to the labelled sample from the downstream task. We
train our model on two HSI datasets, namely Houston dataset (from data fusion
contest, 2013) and Pavia university dataset, and show that the proposed
approach performs better than self-supervised approach and supervised training.</abstract><doi>10.48550/arxiv.2306.10955</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2306.10955 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2306_10955 |
source | arXiv.org |
subjects | Computer Science - Computer Vision and Pattern Recognition |
title | Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T09%3A55%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Semi-Supervised%20Learning%20for%20hyperspectral%20images%20by%20non%20parametrically%20predicting%20view%20assignment&rft.au=Pande,%20Shivam&rft.date=2023-06-19&rft_id=info:doi/10.48550/arxiv.2306.10955&rft_dat=%3Carxiv_GOX%3E2306_10955%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |