Towards Visual Classification Under Class Ambiguity
Viktor Kozák,Jan Mikula,Lukáš Bertl,Karel Košnar,Libor Přeučil,Viktor Kozák,Jan Mikula,Lukáš Bertl,Karel Košnar,Libor Přeučil
Visual classification under uncertainty is a complex computer vision problem. We present a thorough comparison of several variants of convolutional neural network (CNN) classification techniques in the context of ambiguous image data interpretation. We explore possible improvements in classification accuracy achieved by insertion of prior ambiguity information during the annotation process. This e...
