Resumen
Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem. This approach attempts to discriminate between positive (relevant) and negative (irrelevant) items. However, it undergoes a critical weakness. Given a query, it cannot discriminate weakly relevant items, for instance, items of the same type but different color or texture as the given query, which could be a serious limitation for many real-world search applications. Therefore, in this work, we present a quadruplet-based architecture that overcomes the aforementioned weakness. Moreover, we present an instance of this quadruplet network, which we call Sketch-QNet, to deal with the color sketch-based image retrieval (CSBIR) problem, achieving new state-of-the-art results.
Idioma original | Inglés |
---|---|
Título de la publicación alojada | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
Editorial | IEEE Computer Society |
Páginas | 2134-2141 |
Número de páginas | 8 |
ISBN (versión digital) | 9781665448994 |
DOI | |
Estado | Publicada - jun. 2021 |
Publicado de forma externa | Sí |
Evento | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, Estados Unidos Duración: 19 jun. 2021 → 25 jun. 2021 |
Serie de la publicación
Nombre | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
---|---|
ISSN (versión impresa) | 2160-7508 |
ISSN (versión digital) | 2160-7516 |
Conferencia
Conferencia | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
---|---|
País/Territorio | Estados Unidos |
Ciudad | Virtual, Online |
Período | 19/06/21 → 25/06/21 |
Nota bibliográfica
Publisher Copyright:© 2021 IEEE.