Cargando…
Semantic Segmentation Using Pixel-Wise Adaptive Label Smoothing via Self-Knowledge Distillation for Limited Labeling Data
To achieve high performance, most deep convolutional neural networks (DCNNs) require a significant amount of training data with ground truth labels. However, creating ground-truth labels for semantic segmentation requires more time, human effort, and cost compared with other tasks such as classifica...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9003518/ https://www.ncbi.nlm.nih.gov/pubmed/35408237 http://dx.doi.org/10.3390/s22072623 |