papers AI Learner
The Github is limit! Click to go to the new site.

Attentive Single-Tasking of Multiple Tasks

2019-04-18
Kevis-Kokitsi Maninis, Ilija Radosavovic, Iasonas Kokkinos

Abstract

In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as “single-tasking multiple tasks”. The network thus modifies its behaviour through task-dependent feature adaptation, or task attention. This gives the network the ability to accentuate the features that are adapted to a task, while shunning irrelevant ones. We further reduce task interference by forcing the task gradients to be statistically indistinguishable through adversarial training, ensuring that the common backbone architecture serving all tasks is not dominated by any of the task-specific gradients. Results in three multi-task dense labelling problems consistently show: (i) a large reduction in the number of parameters while preserving, or even improving performance and (ii) a smooth trade-off between computation and multi-task accuracy. We provide our system’s code and pre-trained models at this http URL

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08918

PDF

http://arxiv.org/pdf/1904.08918


Similar Posts

Comments