Learning Multiple Dense Prediction Tasks from Partially Annotated Data. (arXiv:2111.14893v3 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2111.14893

Despite the recent advances in multi-task learning of dense prediction
problems, most methods rely on expensive labelled datasets. In this paper, we
present a label efficient approach and look at jointly learning of multiple
dense prediction tasks on partially annotated data (i.e. not all the task
labels are available for each image), which we call multi-task
partially-supervised learning. We propose a multi-task training procedure that
successfully leverages task relations to supervise its multi-task learning when
data is partially annotated. In …

annotated data arxiv cv data learning prediction