Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks
In DCNNs, the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Our proposal makes pointwise convolutions parameter efficient via grouping filters into parallel branches...
Bewaard in:
| Hoofdauteurs: | , , , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
Brno University of Technology
2022-06-01
|
| Reeks: | Mendel |
| Onderwerpen: | |
| Online toegang: | https://mendel-journal.org/index.php/mendel/article/view/169 |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|