Simplification of Deep Neural Network-Based Object Detector for Real-Time Edge Computing

This paper presents a method for simplifying and quantizing a deep neural network (DNN)-based object detector to embed it into a real-time edge device. For network simplification, this paper compares five methods for applying channel pruning to a residual block because special care must be taken reg...

Descripción completa

Detalles Bibliográficos
Autores principales: Choi, Kyoungtaek, Wi, Seong Min, Jung, Ho Gi, Suhr, Jae Kyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099208/
https://www.ncbi.nlm.nih.gov/pubmed/37050837
http://dx.doi.org/10.3390/s23073777

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099208/
https://www.ncbi.nlm.nih.gov/pubmed/37050837
http://dx.doi.org/10.3390/s23073777

Ejemplares similares