Cargando…
The developmental trajectory of object recognition robustness: Children are like small adults but unlike big deep neural networks
In laboratory object recognition tasks based on undistorted photographs, both adult humans and deep neural networks (DNNs) perform close to ceiling. Unlike adults’, whose object recognition performance is robust against a wide range of image distortions, DNNs trained on standard ImageNet (1.3M image...
Autores principales: | Huber, Lukas S., Geirhos, Robert, Wichmann, Felix A. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10337805/ https://www.ncbi.nlm.nih.gov/pubmed/37410494 http://dx.doi.org/10.1167/jov.23.7.4 |
Ejemplares similares
-
General anesthesia and sleep: like and unlike
por: Jung, Jieun, et al.
Publicado: (2022) -
Robust Korean License Plate Recognition Based on Deep Neural Networks
por: Wang, Hanxiang, et al.
Publicado: (2021) -
DRESS syndrome: an unlikely diagnosis with an unlikely cause
por: Soares, Sofia Garcês, et al.
Publicado: (2022) -
Robust deep learning object recognition models rely on low frequency information in natural images
por: Li, Zhe, et al.
Publicado: (2023) -
Feature Recognition of English Based on Deep Belief Neural Network and Big Data Analysis
por: Liu, Xiaoling
Publicado: (2021)