# Multi-Task Learning for Dense Prediction Tasks: A Survey

arXiv: https://arxiv.org/abs/2004.13379 · HTML: https://mlsanity.com/paper/2004.13379/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 28 of 28)

- [Pixel-wise Anomaly Detection in Complex Driving Scenes](https://mlsanity.com/paper/2103.05445/) (2021)
- [Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes](https://mlsanity.com/paper/2111.12264/) (2021)
- [Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07830/) (2021)
- [Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs](https://mlsanity.com/paper/2103.09499/) (2021)
- [Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models](https://mlsanity.com/paper/2310.00566/) (2023)
- [Heterogeneous Multi-task Learning with Expert Diversity](https://mlsanity.com/paper/2106.10595/) (2021)
- [Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral](https://mlsanity.com/paper/2108.11346/) (2021)
- [SpeechNet: A Universal Modularized Model for Speech Processing Tasks](https://mlsanity.com/paper/2105.03070/) (2021)
- [CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen](https://mlsanity.com/paper/2312.05538/) (2023)
- [Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance](https://mlsanity.com/paper/2508.21741/) (2025)
- [Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection](https://mlsanity.com/paper/2103.05354/) (2021)
- [UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks](https://mlsanity.com/paper/2108.04584/) (2021)
- [A Tree-Structured Multi-Task Model Recommender](https://mlsanity.com/paper/2203.05092/) (2022)
- [Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment](https://mlsanity.com/paper/2308.08696/) (2023)
- [Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach](https://mlsanity.com/paper/2201.03326/) (2022)
- [Instance-Level Task Parameters: A Robust Multi-task Weighting Framework](https://mlsanity.com/paper/2106.06129/) (2021)
- [Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis](https://mlsanity.com/paper/2505.06271/) (2025)
- [Multi-task Learning for Concurrent Prediction of Thermal Comfort, Sensation, and Preference](https://mlsanity.com/paper/2204.12380/) (2022)
- [A Multitask Deep Learning Model for Classification and Regression of Hyperspectral Images: Application to the large-scale dataset](https://mlsanity.com/paper/2407.16384/) (2024)
- [Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training](https://mlsanity.com/paper/2509.03975/) (2025)
- [Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT](https://mlsanity.com/paper/2103.03931/) (2021)
- [Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing](https://mlsanity.com/paper/2211.08290/) (2022)
- [Adaptive Pattern Extraction Multi-Task Learning for Multi-Step Conversion Estimations](https://mlsanity.com/paper/2301.02494/) (2023)
- [Parameterized Neural Networks for Finance](https://mlsanity.com/paper/2304.08883/) (2023)
- [DsMtGCN: A Direction-sensitive Multi-task framework for Knowledge Graph Completion](https://mlsanity.com/paper/2306.10290/) (2023)
- [VKIE: The Application of Key Information Extraction on Video Text](https://mlsanity.com/paper/2310.11650/) (2023)
- [For the Misgendered Chinese in Gender Bias Research: Multi-Task Learning with Knowledge Distillation for Pinyin Name-Gender Prediction](https://mlsanity.com/paper/2405.06221/) (2024)
- [αVIL: Learning to Leverage Auxiliary Tasks for Multitask Learning](https://mlsanity.com/paper/2405.07769/) (2024)

## Abstract (arXiv)

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.