# Taskology: Utilizing Task Relations at Scale

arXiv: https://arxiv.org/abs/2005.07289 · HTML: https://mlsanity.com/paper/2005.07289/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2020.

## Built on by (most cited first, 19 of 19)

- [Learning Multiple Dense Prediction Tasks from Partially Annotated Data](https://mlsanity.com/paper/2111.14893/) (2021)
- [Single Image Depth Estimation: An Overview](https://mlsanity.com/paper/2104.06456/) (2021)
- [Label-Assemble: Leveraging Multiple Datasets with Partial Labels](https://mlsanity.com/paper/2109.12265/) (2021)
- [ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.12417/) (2022)
- [Joint-Task Regularization for Partially Labeled Multi-Task Learning](https://mlsanity.com/paper/2404.01976/) (2024)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data](https://mlsanity.com/paper/2409.13251/) (2024)
- [Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions](https://mlsanity.com/paper/2411.18823/) (2024)
- [SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data](https://mlsanity.com/paper/2207.08979/) (2022)
- [Consistent Multimodal Generation via A Unified GAN Framework](https://mlsanity.com/paper/2307.01425/) (2023)
- [Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data](https://mlsanity.com/paper/2311.04040/) (2023)
- [Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models](https://mlsanity.com/paper/2303.16133/) (2023)
- [Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection](https://mlsanity.com/paper/2309.06288/) (2023)
- [StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets](https://mlsanity.com/paper/2506.08013/) (2025)
- [Fantastic Data and How to Query Them](https://mlsanity.com/paper/2201.05026/) (2022)
- [Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharing](https://mlsanity.com/paper/2208.09427/) (2022)
- [JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition](https://mlsanity.com/paper/2308.04934/) (2023)
- [CARLS: Cross-platform Asynchronous Representation Learning System](https://mlsanity.com/paper/2105.12849/) (2021)
- [Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning](https://mlsanity.com/paper/2411.17536/) (2024)

## Abstract (arXiv)

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships among collections of tasks, as they are trained jointly, supervising each other through their known relationships via consistency losses. Furthermore, explicitly utilizing the relationships between tasks allows improving their performance while dramatically reducing the need for labeled data, and allows training with additional unsupervised or simulated data. We demonstrate a distributed joint training algorithm with task-level parallelism, which affords a high degree of asynchronicity and robustness. This allows learning across multiple tasks, or with large amounts of input data, at scale. We demonstrate our framework on subsets of the following collection of tasks: depth and normal prediction, semantic segmentation, 3D motion and ego-motion estimation, and object tracking and 3D detection in point clouds. We observe improved performance across these tasks, especially in the low-label regime.