Leveraging Unlabeled Data for Sketch-based Understanding
| dc.coverage | DOI: 10.1109/CVPRW56347.2022.00563 | |
| dc.creator | Morales, Javier | |
| dc.creator | Murrugarra-Llerena, Nils | |
| dc.creator | Saavedra, Jose M. | |
| dc.date | 2022 | |
| dc.date.accessioned | 2025-11-18T19:53:12Z | |
| dc.date.available | 2025-11-18T19:53:12Z | |
| dc.description | <p>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.</p> | eng |
| dc.identifier | https://investigadores.uandes.cl/en/publications/30cf848b-1920-4447-8d0d-0c25d828ce6e | |
| dc.identifier.uri | https://repositorio.uandes.cl/handle/uandes/58120 | |
| dc.language | eng | |
| dc.rights | info:eu-repo/semantics/restrictedAccess | |
| dc.source | (2022) p.5149-5158 | |
| dc.title | Leveraging Unlabeled Data for Sketch-based Understanding | eng |
| dc.type | Conference article | eng |
| dc.type | Artículo de la conferencia | spa |