Print Email Facebook Twitter Full Color Deep Networks Title Full Color Deep Networks Author Tahur, Nishad (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Pattern Recognition and Bioinformatics) Contributor van Gemert, J.C. (mentor) Tömen, N. (mentor) Lengyel, A. (mentor) Höllt, T. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science Date 2022-06-28 Abstract 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. Subject Convolutional Neural NetworkRetaining Color Dimension3D Convolutions To reference this document use: http://resolver.tudelft.nl/uuid:0b50cfc0-d496-4aac-8ee5-1f4b55c1a165 Part of collection Student theses Document type master thesis Rights © 2022 Nishad Tahur Files PDF MSc_Thesis_Nishad_Tahur.pdf 14.14 MB Close viewer /islandora/object/uuid:0b50cfc0-d496-4aac-8ee5-1f4b55c1a165/datastream/OBJ/view