Cargando…
Domain randomization for neural network classification
Large data requirements are often the main hurdle in training neural networks. Convolutional neural network (CNN) classifiers in particular require tens of thousands of pre-labeled images per category to approach human-level accuracy, while often failing to generalized to out-of-domain test sets. Th...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Springer International Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8570318/ https://www.ncbi.nlm.nih.gov/pubmed/34760433 http://dx.doi.org/10.1186/s40537-021-00455-5 |