Multilayer Semantic Features Adaptive Distillation for Object Detectors

Knowledge distillation (KD) is a well-established technique for compressing neural networks and has gained increasing attention in object detection tasks. However, typical object detection distillation methods use fixed-level semantic features for distillation, which might not be best for all traini...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Zhenchang, Liu, Jinqiang, Chen, Yuping, Mei, Wang, Huang, Fuzhong, Chen, Lei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490649/
https://www.ncbi.nlm.nih.gov/pubmed/37688070
http://dx.doi.org/10.3390/s23177613

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490649/
https://www.ncbi.nlm.nih.gov/pubmed/37688070
http://dx.doi.org/10.3390/s23177613

Ejemplares similares