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: | Dagaev, Nikolay, Roads, Brett D., Luo, Xiaoliang, Barry, Daniel N., Patil, Kaustubh R., Love, Bradley C. |
---|---|
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 |
Ejemplares similares
-
Palliative Care: Too Good to Be True?
por: Senderovich, Helen, et al.
Publicado: (2020) -
Commentary: If it looks too good to be true, it probably is
por: Sellke, Frank W.
Publicado: (2021) -
Ivermectin for the Treatment of COVID-19 Disease: Too Good to Pass Up or Too Good to Be True?
por: Siedner, Mark J
Publicado: (2021) -
The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks
por: Luo, Xiaoliang, et al.
Publicado: (2021) -
Battling quiescence for tumor eradication: too good to be true?
por: McCarty, Nami
Publicado: (2018)