Full Color Deep Networks

Full Color Deep Networks

Tahur, Nishad (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Pattern Recognition and Bioinformatics)

van Gemert, J.C. (mentor)
Tömen, N. (mentor)
Lengyel, A. (mentor)
Höllt, T. (graduation committee)

Delft University of Technology

Computer Science

2022-06-28

Color information has been shown to provide useful information during image classification. Yet current popular deep convolutional neural networks use 2-dimensional convolutional layers. The first 2-dimensional convolutional layer in the network combines the color channels of the input images, which produces feature maps per channel with only spatial dimensions, height and width, getting rid of the color dimension. In this work we introduce Full Color Deep networks which use 3-dimensional convolutions to retain the color dimension beyond the first layer. The 3D kernels convolve over the color and spatial dimensions. The network can extract features from all three dimensions in all layers which are subsequently used by the classifier. We show that the Full Color Deep networks perform at least as well as the current CNNs but outperform them in learning color information and using that information in other downstream tasks.

Convolutional Neural Network
Retaining Color Dimension
3D Convolutions

http://resolver.tudelft.nl/uuid:0b50cfc0-d496-4aac-8ee5-1f4b55c1a165

Student theses

master thesis

© 2022 Nishad Tahur