Module of Axis-based Nexus Attention for weakly supervised object localization

Weakly supervised object localization tasks remain challenging to identify and segment an entire object rather than only discriminative parts of the object. To tackle this problem, corruption-based approaches have been devised, which involve the training of non-discriminative regions by corrupting (...

Descripción completa

Detalles Bibliográficos
Autores principales: Sohn, Junghyo, Jeon, Eunjin, Jung, Wonsik, Kang, Eunsong, Suk, Heung-Il
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10616293/
https://www.ncbi.nlm.nih.gov/pubmed/37903879
http://dx.doi.org/10.1038/s41598-023-45796-8

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10616293/
https://www.ncbi.nlm.nih.gov/pubmed/37903879
http://dx.doi.org/10.1038/s41598-023-45796-8

Ejemplares similares