Advanced Methods and Deep Learning in Computer Vision

Chapter 8: Domain adaptation and continual learning in semantic segmentation

Umberto Michieli; Marco Toldo; Pietro Zanuttigh    Department of Information Engineering, University of Padova, Padova, Italy

Abstract

Deep networks produce outstanding results in many computer vision tasks including semantic segmentation. On the other hand, they are plagued by the need of a huge amount of labeled data for training, which is not always available or may not be accessible all together as typically required in the standard supervised machine learning setting. These problems raise the demand for knowledge transfer techniques able to adapt the learning performed on one domain to a related one and to allow the training of the network in multiple stages. This ...