What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance.
Mahmoud AfifiMichael S. BrownPublished in: CoRR (2019)
Keyphrases
- deep learning
- color constancy
- neural network
- unsupervised feature learning
- deep architectures
- unsupervised learning
- machine learning
- human vision
- mental models
- deep belief networks
- back propagation
- color constancy algorithms
- weakly supervised
- gamut mapping
- artificial neural networks
- pattern recognition
- natural images
- feed forward
- face recognition
- image segmentation