A non-negative feedback self-distillation method for salient object detection

Self-distillation methods utilize Kullback-Leibler divergence (KL) loss to transfer the knowledge from the network itself, which can improve the model performance without increasing computational resources and complexity. However, when applied to salient object detection (SOD), it is difficult to ef...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Lei, Cao, Tieyong, Zheng, Yunfei, Yang, Jibin, Wang, Yang, Wang, Yekui, Zhang, Bo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10319267/
https://www.ncbi.nlm.nih.gov/pubmed/37409081
http://dx.doi.org/10.7717/peerj-cs.1435

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10319267/
https://www.ncbi.nlm.nih.gov/pubmed/37409081
http://dx.doi.org/10.7717/peerj-cs.1435

Ejemplares similares