# Partly Supervised Multitask Learning

arXiv: https://arxiv.org/abs/2005.02523 · HTML: https://mlsanity.com/paper/2005.02523/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 11 of 11)

- [Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias](https://mlsanity.com/paper/2310.14814/) (2023)
- [Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption](https://mlsanity.com/paper/2310.13434/) (2023)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data](https://mlsanity.com/paper/2110.13185/) (2021)
- [Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models](https://mlsanity.com/paper/2404.13239/) (2024)
- [Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data](https://mlsanity.com/paper/2311.04040/) (2023)
- [Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection](https://mlsanity.com/paper/2309.06288/) (2023)
- [Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning](https://mlsanity.com/paper/2403.10252/) (2024)
- [Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels](https://mlsanity.com/paper/2306.08839/) (2023)
- [Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning](https://mlsanity.com/paper/2411.17536/) (2024)
- [Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning](https://mlsanity.com/paper/2605.17624/) (2026)

## Abstract (arXiv)

Semi-supervised learning has recently been attracting attention as an alternative to fully supervised models that require large pools of labeled data. Moreover, optimizing a model for multiple tasks can provide better generalizability than single-task learning. Leveraging self-supervision and adversarial training, we propose a novel general purpose semi-supervised, multiple-task model---namely, self-supervised, semi-supervised, multitask learning (S4MTL)---for accomplishing two important tasks in medical imaging, segmentation and diagnostic classification. Experimental results on chest and spine X-ray datasets suggest that our S4MTL model significantly outperforms semi-supervised single task, semi/fully-supervised multitask, and fully-supervised single task models, even with a 50% reduction of class and segmentation labels. We hypothesize that our proposed model can be effective in tackling limited annotation problems for joint training, not only in medical imaging domains, but also for general-purpose vision tasks.