Search Results for author:
Found 6 papers, 3 papers with code
Human vs Objective Evaluation of Colourisation Performance
There is also evidence that human observers are most intolerant to an incorrect hue of naturally occurring objects.
A spatial hue similarity measure for assessment of colourisation
Automatic colourisation of grey-scale images is an ill-posed multi-modal problem.
Batch Normalization in the final layer of generative networks
This paper will show that this is not necessarily a good heuristic and that Batch Normalization can be beneficial in the final layer of the generator network either by placing it before the final non-linear activation, usually a $tanh$ or replacing the final $tanh$ activation altogether with Batch Normalization and clipping.
Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification
Deep learning methods have shown impressive results and are now the new state of the art for a wide range of computer vision tasks including image and video recognition and segmentation.
Texture segmentation with Fully Convolutional Networks
We show in particular that these networks can learn to recognize and segment a type of texture, e. g. wood and grass from texture recognition datasets (no training segmentation).
Using Filter Banks in Convolutional Neural Networks for Texture Classification
Its architecture is indeed well suited to object analysis by learning and classifying complex (deep) features that represent parts of an object or the object itself.
