Improving object detection quality with structural constraints

Recent researches revealed object detection networks using the simple “classification loss + localization loss” training objective are not effectively optimized in many cases, while providing additional constraints on network features could effectively improve object detection quality. Specifically,...

Descripción completa

Detalles Bibliográficos
Autores principales: Rong, Zihao, Wang, Shaofan, Kong, Dehui, Yin, Baocai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9116628/
https://www.ncbi.nlm.nih.gov/pubmed/35584103
http://dx.doi.org/10.1371/journal.pone.0267863

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9116628/
https://www.ncbi.nlm.nih.gov/pubmed/35584103
http://dx.doi.org/10.1371/journal.pone.0267863

Ejemplares similares