AutoMTL: A Programming Framework for Automated Multi-Task Learning
Year: 2021
Type: preprint
Abstract: Multi-task learning (MTL) jointly learns a set of tasks. It is a promising approach to reduce the training and inference time and storage costs while improving prediction accuracy and generalization performance for many computer vision tasks. However, a major barrier preventing the widespread adoption of MTL is the lack of systematic support for developing compact multi-task models given a set of tasks. In this paper, we aim to remove the barrier by developing the first programming framework AutoMTL that automates MTL model development. AutoMTL takes as inputs an arbitrary backbone convolutional neural network and a set of tasks to learn, then automatically produce a multi-task model that achieves high accuracy and has small memory footprint simultaneously. As a programming framework, AutoMTL could facilitate the development of MTL-enabled computer vision applications and even further improve task performance. Code of AutoMTL will be available at https://github.com/zhanglijun95/AutoMTL
Source: arXiv (Cornell University)
Authors: Lijun Zhang, Xiao Liu, Hui Guan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3208137556