Leveraging Unlabeled Data for Sketch-based Understanding

Javier Morales*, Nils Murrugarra-Llerena*, Jose M. Saavedra*

*Autor correspondiente de este trabajo

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

Sketch-based understanding is a critical component of human cognitive learning and is a primitive communication means between humans. This topic has recently attracted the interest of the computer vision community as sketching represents a powerful tool to express static objects and dynamic scenes. Unfortunately, despite its broad application domains, the current sketch-based models strongly rely on labels for supervised training, ignoring knowledge from unlabeled data, thus limiting the underlying generalization and the applicability. Therefore, we present a study about the use of unlabeled data to improve a sketch-based model. To this end, we evaluate variations of VAE and semi-supervised VAE, and present an extension of BYOL to deal with sketches. Our results show the superiority of sketch-BYOL, which outperforms other self-supervised approaches increasing the retrieval performance for known and unknown categories. Furthermore, we show how other tasks can benefit from our proposal.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
EditorialIEEE Computer Society
Páginas5149-5158
Número de páginas10
ISBN (versión digital)9781665487399
DOI
EstadoPublicada - 2022
Evento2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 - New Orleans, Estados Unidos
Duración: 19 jun. 202220 jun. 2022

Serie de la publicación

NombreIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volumen2022-June
ISSN (versión impresa)2160-7508
ISSN (versión digital)2160-7516

Conferencia

Conferencia2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
País/TerritorioEstados Unidos
CiudadNew Orleans
Período19/06/2220/06/22

Nota bibliográfica

Publisher Copyright:
© 2022 IEEE.

Huella

Profundice en los temas de investigación de 'Leveraging Unlabeled Data for Sketch-based Understanding'. En conjunto forman una huella única.

Citar esto