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

May 5, 2022, 1:10 a.m. | Wei-Hong Li, Xialei Liu, Hakan Bilen

cs.CV updates on arXiv.org arxiv.org

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

More from arxiv.org / cs.CV updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California