# Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels

arXiv: https://arxiv.org/abs/2306.08839 · HTML: https://mlsanity.com/paper/2306.08839/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [An Overview of Deep Semi-Supervised Learning](https://mlsanity.com/paper/2006.05278/) (2020)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis](https://mlsanity.com/paper/1709.09930/) (2017)
- [Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts](https://mlsanity.com/paper/2004.07684/) (2020)
- [When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework](https://mlsanity.com/paper/2103.01520/) (2021)
- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures](https://mlsanity.com/paper/2208.08605/) (2022)
- [Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks](https://mlsanity.com/paper/1802.04962/) (2018)
- [Partly Supervised Multitask Learning](https://mlsanity.com/paper/2005.02523/) (2020)
- [UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval](https://mlsanity.com/paper/2209.02522/) (2022)
- [Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets](https://mlsanity.com/paper/2003.06746/) (2020)
- [EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Images](https://mlsanity.com/paper/2112.11610/) (2021)

## Built on by (most cited first, 1 of 1)

- [NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks](https://mlsanity.com/paper/2512.06251/) (2025)

## Abstract (arXiv)

In real-world scenarios we often need to perform multiple tasks simultaneously. Multi-Task Learning (MTL) is an adequate method to do so, but usually requires datasets labeled for all tasks. We propose a method that can leverage datasets labeled for only some of the tasks in the MTL framework. Our work, Knowledge Assembly (KA), learns multiple tasks from disjoint datasets by leveraging the unlabeled data in a semi-supervised manner, using model augmentation for pseudo-supervision. Whilst KA can be implemented on any existing MTL networks, we test our method on jointly learning person re-identification (reID) and pedestrian attribute recognition (PAR). We surpass the single task fully-supervised performance by 4.2% points for reID and 0.9% points for PAR.