| Topic: | Learning multilayer classifiers with weak annotations |
|---|
| Department: | Algoritmy pro biomedicínské zobrazování |
|---|
| Supervisor: | prof. Dr. Ing. Jan Kybic |
|---|
| Announce as: | Diplomová práce, Bakalářská práce, Semestrální projekt |
|---|
| Description: | 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. |
|---|
