Multi-Task Learning for Dense Prediction Tasks: A Survey

TL;DR

This survey reviews recent deep learning approaches for multi-task learning in dense prediction tasks, highlighting architectural and optimization strategies, and providing extensive experimental comparisons across benchmarks.

Contribution

It offers a comprehensive overview of state-of-the-art MTL methods for dense prediction, analyzing architectures, optimization techniques, and experimental results.

Findings

Multi-task learning improves performance and efficiency in dense prediction tasks.

Different MTL architectures have distinct advantages and trade-offs.

Experimental results highlight strengths and weaknesses of various methods.

Abstract

With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural network is trained for each individual task. Yet, recent multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint, by jointly tackling multiple tasks through a learned shared representation. In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision, explicitly emphasizing on dense prediction tasks. Our contributions concern the following. First, we consider MTL from a network architecture point-of-view. We include an extensive overview and discuss the advantages/disadvantages of recent popular MTL models. Second, we examine various optimization methods to tackle the joint learning of multiple tasks. We summarize the qualitative elements of these works and explore their commonalities and differences. Finally, we provide an extensive experimental evaluation across a variety of dense prediction benchmarks to examine the pros and cons of the different methods, including both architectural and optimization based strategies.