Joint-Task Regularization for Partially Labeled Multi-Task Learning

arXiv:2404.01976v1 Announce Type: cross
Abstract: Multi-task learning has become increasingly popular in the machine learning field, but its practicality is hindered by the need for large, labeled datasets. Most multi-task learning methods depend on fully labeled datasets wherein each input example is accompanied by ground-truth labels for all target tasks. Unfortunately, curating such datasets can be prohibitively expensive and impractical, especially for dense prediction tasks which require per-pixel labels for each image. With this in mind, we propose Joint-Task Regularization …

abstract arxiv become cs.ai cs.cv cs.lg datasets example ground-truth labels machine machine learning multi-task learning popular regularization tasks truth type