Enhancing few-shot object detection through pseudo-label mining

Few-shot object detection involves adapting an existing detector to a set of unseen categories with few annotated examples. This data limitation makes these methods to underperform those trained on large labeled datasets. In many scenarios, there is a high amount of unlabeled data that is never expl...

Descripción completa

Detalles Bibliográficos
Autores: García Fernández, Pablo, Cores Costa, Daniel, Mucientes Molina, Manuel
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/39982
Acceso en línea:https://hdl.handle.net/10347/39982
Access Level:acceso abierto
Palabra clave:Few-shot
Object detection
Few-shot learning
Pseudo-label mining
Pseudo-labeling
120304 Inteligencia artificial
id ES_49f1fc36b28d45fddba8a2a5cb81ee13
oai_identifier_str oai:minerva.usc.gal:10347/39982
network_acronym_str ES
network_name_str España
repository_id_str
spelling Enhancing few-shot object detection through pseudo-label miningGarcía Fernández, PabloCores Costa, DanielMucientes Molina, ManuelFew-shotObject detectionFew-shot learningPseudo-label miningPseudo-labeling120304 Inteligencia artificialFew-shot object detection involves adapting an existing detector to a set of unseen categories with few annotated examples. This data limitation makes these methods to underperform those trained on large labeled datasets. In many scenarios, there is a high amount of unlabeled data that is never exploited. Thus, we propose to exPAND the initial novel set by mining pseudo-labels. From a raw set of detections, xPAND obtains reliable pseudo-labels suitable for training any detector. To this end, we propose two new modules: Class and Box confirmation. Class Confirmation aims to remove misclassified pseudo-labels by comparing candidates with expected class prototypes. Box Confirmation estimates IoU to discard inadequately framed objects. Experimental results demonstrate that xPAND enhances the performance of multiple detectors up to +5.9 nAP and +16.4 nAP50 points for MS-COCO and PASCAL VOC, respectively, establishing a new state of the art. Code: https://github.com/PAGF188/xPANDElsevierUniversidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)Universidade de Santiago de Compostela. Departamento de Electrónica e Computación20252025-02-0120252025-02-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10347/39982reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-112623GB-I00 IA RESPONSABLE PARA MINERIA DE PROCESOS 2.0Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-149549NB-I00 APROVECHANDO LA INTELIGENCIA ARTIFICIAL PARA UNA MONITORIZACION PREDICTIVA ROBUSTA EN MINERIA DE PROCESOSopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/399822026-06-15T12:47:27Z
dc.title.none.fl_str_mv Enhancing few-shot object detection through pseudo-label mining
title Enhancing few-shot object detection through pseudo-label mining
spellingShingle Enhancing few-shot object detection through pseudo-label mining
García Fernández, Pablo
Few-shot
Object detection
Few-shot learning
Pseudo-label mining
Pseudo-labeling
120304 Inteligencia artificial
title_short Enhancing few-shot object detection through pseudo-label mining
title_full Enhancing few-shot object detection through pseudo-label mining
title_fullStr Enhancing few-shot object detection through pseudo-label mining
title_full_unstemmed Enhancing few-shot object detection through pseudo-label mining
title_sort Enhancing few-shot object detection through pseudo-label mining
dc.creator.none.fl_str_mv García Fernández, Pablo
Cores Costa, Daniel
Mucientes Molina, Manuel
author García Fernández, Pablo
author_facet García Fernández, Pablo
Cores Costa, Daniel
Mucientes Molina, Manuel
author_role author
author2 Cores Costa, Daniel
Mucientes Molina, Manuel
author2_role author
author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)
Universidade de Santiago de Compostela. Departamento de Electrónica e Computación
dc.subject.none.fl_str_mv Few-shot
Object detection
Few-shot learning
Pseudo-label mining
Pseudo-labeling
120304 Inteligencia artificial
topic Few-shot
Object detection
Few-shot learning
Pseudo-label mining
Pseudo-labeling
120304 Inteligencia artificial
description Few-shot object detection involves adapting an existing detector to a set of unseen categories with few annotated examples. This data limitation makes these methods to underperform those trained on large labeled datasets. In many scenarios, there is a high amount of unlabeled data that is never exploited. Thus, we propose to exPAND the initial novel set by mining pseudo-labels. From a raw set of detections, xPAND obtains reliable pseudo-labels suitable for training any detector. To this end, we propose two new modules: Class and Box confirmation. Class Confirmation aims to remove misclassified pseudo-labels by comparing candidates with expected class prototypes. Box Confirmation estimates IoU to discard inadequately framed objects. Experimental results demonstrate that xPAND enhances the performance of multiple detectors up to +5.9 nAP and +16.4 nAP50 points for MS-COCO and PASCAL VOC, respectively, establishing a new state of the art. Code: https://github.com/PAGF188/xPAND
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-02-01
2025
2025-02-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10347/39982
url https://hdl.handle.net/10347/39982
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-112623GB-I00 IA RESPONSABLE PARA MINERIA DE PROCESOS 2.0
Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-149549NB-I00 APROVECHANDO LA INTELIGENCIA ARTIFICIAL PARA UNA MONITORIZACION PREDICTIVA ROBUSTA EN MINERIA DE PROCESOS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407455354552320
score 15,811543

Similares en LA Referencia