Short Presentation
in
Affinity Workshop: LXAI Research @ NeurIPS 2020
A Quaternion Monogenic Layer Resilient to Large Brightness Changes in Image Classification
Eduardo Ulises Moya
Abstract:
Conventional CNN cannot guarantee the invariance response even to small changes in input images, for example, with brightness variations. This paper analyzes the performance of a novel convolutional layer in the Fourier domain capable of classifying images even with large alterations of their brightness. The results show that the performance of a given CNN architecture is significantly more resilient to large brightness changes if use the proposed layer.
Chat is not available.