Maninis, K-K; Radosavovic, I; Kokkinos, I; (2019) Attentive Single-Tasking of Multiple Tasks. In: CVPR 2019 - IEEE Conference on Computer Vision and Pattern Recognition. (pp. pp. 1851-1860). Computer Vision Foundation / IEEE: Long Beach, CA, USA. (In press).

Text ASTMT.pdf - Accepted Version Available under License : See the attached licence file. Download (8MB)

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 http://vision.ee.ethz.ch/ ˜kmaninis/astmt/.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item