Cargando…
A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models
In this paper, we propose a new approach to train a deep neural network with multiple intermediate auxiliary classifiers, branching from it. These ‘multi-exits’ models can be used to reduce the inference time by performing early exit on the intermediate branches, if the confidence of the prediction...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774619/ https://www.ncbi.nlm.nih.gov/pubmed/35052027 http://dx.doi.org/10.3390/e24010001 |