Cargando…
Evaluating the progress of deep learning for visual relational concepts
Convolutional neural networks have become the state-of-the-art method for image classification in the last 10 years. Despite the fact that they achieve superhuman classification accuracy on many popular datasets, they often perform much worse on more abstract image classification tasks. We will show...
Autores principales: | Stabinger, Sebastian, Peer, David, Piater, Justus, Rodríguez-Sánchez, Antonio |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8525837/ https://www.ncbi.nlm.nih.gov/pubmed/34636844 http://dx.doi.org/10.1167/jov.21.11.8 |
Ejemplares similares
-
Diversity priors for learning early visual features
por: Xiong, Hanchen, et al.
Publicado: (2015) -
A Push-Pull CORF Model of a Simple Cell with Antiphase Inhibition Improves SNR and Contour Detection
por: Azzopardi, George, et al.
Publicado: (2014) -
Learning Semantics of Gestural Instructions for Human-Robot Collaboration
por: Shukla, Dadhichi, et al.
Publicado: (2018) -
Skill Learning by Autonomous Robotic Playing Using Active Learning and Exploratory Behavior Composition
por: Hangl, Simon, et al.
Publicado: (2020) -
Classification of Tennis Shots with a Neural Network Approach
por: Ganser, Andreas, et al.
Publicado: (2021)