Cargando…
A too-good-to-be-true prior to reduce shortcut reliance()
Despite their impressive performance in object recognition and other tasks under standard testing conditions, deep networks often fail to generalize to out-of-distribution (o.o.d.) samples. One cause for this shortcoming is that modern architectures tend to rely on ǣshortcutsǥ superficial features t...
| Autores principales: | , , , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Elsevier Science
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10615835/ https://www.ncbi.nlm.nih.gov/pubmed/37915616 http://dx.doi.org/10.1016/j.patrec.2022.12.010 |