When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review

TL;DR

This review explores how multi-task learning in computer vision can be effectively utilized under partial supervision to overcome challenges related to data dependency and complex optimization, highlighting recent methods, datasets, and benchmarks.

Contribution

It provides a comprehensive analysis of partial supervision techniques in multi-task learning, including parameter sharing, task grouping, and benchmarking in computer vision.

Findings

Partial supervision reduces data dependency in MTL.

Task grouping improves knowledge transfer between related tasks.

Benchmark datasets facilitate evaluation of partial supervision methods.

Abstract

Multi-Task Learning (MTL) aims to learn multiple tasks simultaneously while exploiting their mutual relationships. By using shared resources to simultaneously calculate multiple outputs, this learning paradigm has the potential to have lower memory requirements and inference times compared to the traditional approach of using separate methods for each task. Previous work in MTL has mainly focused on fully-supervised methods, as task relationships can not only be leveraged to lower the level of data-dependency of those methods but they can also improve performance. However, MTL introduces a set of challenges due to a complex optimisation scheme and a higher labeling requirement. This review focuses on how MTL could be utilised under different partial supervision settings to address these challenges. First, this review analyses how MTL traditionally uses different parameter sharing techniques to transfer knowledge in between tasks. Second, it presents the different challenges arising from such a multi-objective optimisation scheme. Third, it introduces how task groupings can be achieved by analysing task relationships. Fourth, it focuses on how partially supervised methods applied to MTL can tackle the aforementioned challenges. Lastly, this review presents the available datasets, tools and benchmarking results of such methods.