High-contrast "gaudy" images improve the training of deep neural network models of visual cortex.
Benjamin CowleyJonathan W. PillowPublished in: NeurIPS (2020)
Keyphrases
- high contrast
- neural network model
- low contrast
- visual cortex
- neural network
- image analysis
- receptive fields
- network architecture
- fully automatic
- training set
- image data
- input image
- image classification
- natural images
- blood vessels
- primary visual cortex
- region of interest
- artificial neural networks
- image sequences
- computer vision