Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

We propose a new efficient architecture for semantic segmentation, based on a “Waterfall” Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the effi...

Descripción completa

Detalles Bibliográficos
Autores principales: Artacho, Bruno, Savakis, Andreas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960670/
https://www.ncbi.nlm.nih.gov/pubmed/31817366
http://dx.doi.org/10.3390/s19245361

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960670/
https://www.ncbi.nlm.nih.gov/pubmed/31817366
http://dx.doi.org/10.3390/s19245361

Ejemplares similares