Cargando…
The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks
People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and more biased toward the target (a potential cost). Motivated by selective attention...
Autores principales: | Luo, Xiaoliang, Roads, Brett D., Love, Bradley C. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer International Publishing
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550459/ https://www.ncbi.nlm.nih.gov/pubmed/34723095 http://dx.doi.org/10.1007/s42113-021-00098-y |
Ejemplares similares
-
Multiscale Hybrid Convolutional Deep Neural Networks with Channel Attention
por: Yang, Hua, et al.
Publicado: (2022) -
A too-good-to-be-true prior to reduce shortcut reliance()
por: Dagaev, Nikolay, et al.
Publicado: (2023) -
Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition
por: Zhang, Hua, et al.
Publicado: (2021) -
Identification of Apple Leaf Diseases by Improved Deep Convolutional Neural Networks With an Attention Mechanism
por: Wang, Peng, et al.
Publicado: (2021) -
Guiding visual attention in deep convolutional neural networks based on human eye movements
por: van Dyck, Leonard Elia, et al.
Publicado: (2022)