Téma:Learning multilayer classifiers with weak annotations
Vedoucí:Prof. Dr. Ing. Jan Kybic
Vypsáno jako:Diplomová práce,Bakalářská práce,Individuální projekt,Dobrovolná odborná práce,Semestrální projekt
Popis:This topic is similar to deep learning but without neural networks. We chain several classifiers together - for example the first one will do a pixel-wise segmentations and the second will evaluate the shape of the detected objects. The challenge is to train all classifiers in the chain when training data is only available for the final output - a so-called weak labels. We shall start by simulating several simple cases, gradually moving towards a practical method.
Realizace:SW project, theoretical analysis
Vypsáno dne:29.05.2018