Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning

Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embed...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Changkun, Barnes, Nick, Petersson, Lars, Tsuchida, Russell
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 Ye, Changkun
Barnes, Nick
Petersson, Lars
Tsuchida, Russell
description Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.
doi_str_mv 10.48550/arxiv.2210.06120
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_06120</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_06120</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-98924e877a49821b29757ca4628f661ca602ce6dc3ad6a8b78ff89e5041314a73</originalsourceid><addsrcrecordid>eNotz7FOwzAYBGAvDKjwAEz1C6TYjmM7IwolVEoFEp26hD_Ob7CU2sgOCHh6SmE66U466SPkirOVNFXFriF9-o-VEMeCKS7YOXleO-etxzDTFt5z9hDoY4oWc6bbOOJEY6DNBDkXm8MAEwSLI72FGTLOmbqYaIsBE0z--zjsMcXi6TXOtENIwYeXC3LmYMp4-Z8Lsrtb75r7ontoN81NV4DSrKhNLSQarUHWRvBB1LrSFqQSxinFLSgmLKrRljAqMIM2zpkaKyZ5ySXockGWf7cnYv-W_AHSV_9L7U_U8gdgs05e</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning</title><source>arXiv.org</source><creator>Ye, Changkun ; Barnes, Nick ; Petersson, Lars ; Tsuchida, Russell</creator><creatorcontrib>Ye, Changkun ; Barnes, Nick ; Petersson, Lars ; Tsuchida, Russell</creatorcontrib><description>Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.</description><identifier>DOI: 10.48550/arxiv.2210.06120</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.06120$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.06120$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ye, Changkun</creatorcontrib><creatorcontrib>Barnes, Nick</creatorcontrib><creatorcontrib>Petersson, Lars</creatorcontrib><creatorcontrib>Tsuchida, Russell</creatorcontrib><title>Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning</title><description>Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FOwzAYBGAvDKjwAEz1C6TYjmM7IwolVEoFEp26hD_Ob7CU2sgOCHh6SmE66U466SPkirOVNFXFriF9-o-VEMeCKS7YOXleO-etxzDTFt5z9hDoY4oWc6bbOOJEY6DNBDkXm8MAEwSLI72FGTLOmbqYaIsBE0z--zjsMcXi6TXOtENIwYeXC3LmYMp4-Z8Lsrtb75r7ontoN81NV4DSrKhNLSQarUHWRvBB1LrSFqQSxinFLSgmLKrRljAqMIM2zpkaKyZ5ySXockGWf7cnYv-W_AHSV_9L7U_U8gdgs05e</recordid><startdate>20221011</startdate><enddate>20221011</enddate><creator>Ye, Changkun</creator><creator>Barnes, Nick</creator><creator>Petersson, Lars</creator><creator>Tsuchida, Russell</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221011</creationdate><title>Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning</title><author>Ye, Changkun ; Barnes, Nick ; Petersson, Lars ; Tsuchida, Russell</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-98924e877a49821b29757ca4628f661ca602ce6dc3ad6a8b78ff89e5041314a73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Ye, Changkun</creatorcontrib><creatorcontrib>Barnes, Nick</creatorcontrib><creatorcontrib>Petersson, Lars</creatorcontrib><creatorcontrib>Tsuchida, Russell</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ye, Changkun</au><au>Barnes, Nick</au><au>Petersson, Lars</au><au>Tsuchida, Russell</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning</atitle><date>2022-10-11</date><risdate>2022</risdate><abstract>Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.</abstract><doi>10.48550/arxiv.2210.06120</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.06120
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_06120
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T18%3A34%3A10IST&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=Efficient%20Gaussian%20Process%20Model%20on%20Class-Imbalanced%20Datasets%20for%20Generalized%20Zero-Shot%20Learning&rft.au=Ye,%20Changkun&rft.date=2022-10-11&rft_id=info:doi/10.48550/arxiv.2210.06120&rft_dat=%3Carxiv_GOX%3E2210_06120%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