# Feature Partitioning for Efficient Multi-Task Architectures

arXiv: https://arxiv.org/abs/1908.04339 · HTML: https://mlsanity.com/paper/1908.04339/

## Key facts

- Cited by 9 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 12 Aug 2019.

## Built on by (most cited first, 9 of 9)

- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [Multi-Task Learning for Visual Scene Understanding](https://mlsanity.com/paper/2203.14896/) (2022)
- [Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks](https://mlsanity.com/paper/2107.10963/) (2021)
- [Surround-View Cameras based Holistic Visual Perception for Automated Driving](https://mlsanity.com/paper/2206.05542/) (2022)
- [Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction](https://mlsanity.com/paper/2308.10293/) (2023)
- [Simplifying Multi-Task Architectures Through Task-Specific Normalization](https://mlsanity.com/paper/2512.20420/) (2025)
- [Memory Efficient Adaptive Attention For Multiple Domain Learning](https://mlsanity.com/paper/2110.10969/) (2021)
- [Capacity and Redundancy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2607.16554/) (2026)

## Abstract (arXiv)

Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We propose a search space that compactly represents different parameter sharing strategies. This provides more effective coverage and sampling of the space of multi-task architectures. We also present a method for quick evaluation of different architectures by using feature distillation. Together these contributions allow us to quickly optimize for efficient multi-task models. We benchmark on Visual Decathlon, demonstrating that we can automatically search for and identify multi-task architectures that effectively make trade-offs between task resource requirements while achieving a high level of final performance.