Source-Free Video Unsupervised Domain Adaptation (SFVUDA) methods consis...
To overcome the domain gap between synthetic and real-world datasets,
un...
Class-incremental semantic image segmentation assumes multiple model upd...
Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the tas...
Adapting a segmentation model from a labeled source domain to a target
d...
Discovering novel concepts from unlabelled data and in a continuous mann...
In an effort to reduce annotation costs in action recognition, unsupervi...
In this work we address multi-target domain adaptation (MTDA) in semanti...
Source-free domain adaptation (SFDA) aims to adapt a classifier to an
un...
We study the new task of class-incremental Novel Class Discovery
(class-...
In this paper, we address Novel Class Discovery (NCD), the task of unvei...
In this paper we address multi-target domain adaptation (MTDA), where gi...
Most domain adaptation methods consider the problem of transferring know...
Recent co-part segmentation methods mostly operate in a supervised learn...
Designing neural networks for object recognition requires considerable
a...
Hashing methods have been recently found very effective in retrieval of
...
A classifier trained on a dataset seldom works on other datasets obtaine...