Search Results for author:
Found 3 papers, 2 papers with code
Learning Representation in Colour Conversion
Our results show, with respect to the baseline network (whose input and output are RGB) 5-10% higher classification accuracy is obtained with decorrelating ColourConvNets.
Deep Neural Models for color discrimination and color constancy
High levels of color constancy were achieved with different DNN architectures.
The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
We also observed that the learnt embedding space is easier to interpret in colour opponent models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
