Загрузка...
Efficient-CapsNet: capsule network with self-attention routing
Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of feature...
Сохранить в:
| Опубликовано в: : | Sci Rep |
|---|---|
| Главные авторы: | , , |
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
Nature Publishing Group UK
2021
|
| Предметы: | |
| Online-ссылка: | https://ncbi.nlm.nih.gov/pmc/articles/PMC8290018/ https://ncbi.nlm.nih.gov/pubmed/34282164 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1038/s41598-021-93977-0 |
| Метки: |
Добавить метку
Нет меток, Требуется 1-ая метка записи!
|