Cargando…
Multi-Level and Multi-Scale Feature Aggregation Network for Semantic Segmentation in Vehicle-Mounted Scenes
The main challenges of semantic segmentation in vehicle-mounted scenes are object scale variation and trading off model accuracy and efficiency. Lightweight backbone networks for semantic segmentation usually extract single-scale features layer-by-layer only by using a fixed receptive field. Most mo...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8126014/ https://www.ncbi.nlm.nih.gov/pubmed/34065155 http://dx.doi.org/10.3390/s21093270 |