DeepAI AI Chat
Log In Sign Up

Learning Task Relatedness in Multi-Task Learning for Images in Context

by   Gjorgji Strezoski, et al.
University of Amsterdam

Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are explicitly defined based on domain knowledge multi-task learning (MTL) offers such concurrent solutions, while exploiting relatedness between multiple tasks performed over the same dataset. In most cases however, this relatedness is not explicitly defined and the domain expert knowledge that defines it is not available. To address this issue, we introduce Selective Sharing, a method that learns the inter-task relatedness from secondary latent features while the model trains. Using this insight, we can automatically group tasks and allow them to share knowledge in a mutually beneficial way. We support our method with experiments on 5 datasets in classification, regression, and ranking tasks and compare to strong baselines and state-of-the-art approaches showing a consistent improvement in terms of accuracy and parameter counts. In addition, we perform an activation region analysis showing how Selective Sharing affects the learned representation.


page 7

page 8

page 11

page 12


Efficient Computation Sharing for Multi-Task Visual Scene Understanding

Solving multiple visual tasks using individual models can be resource-in...

Learning Sparse Sharing Architectures for Multiple Tasks

Most existing deep multi-task learning models are based on parameter sha...

Learning Task Grouping and Overlap in Multi-task Learning

In the paradigm of multi-task learning, mul- tiple related prediction ta...

Many Task Learning with Task Routing

Typical multi-task learning (MTL) methods rely on architectural adjustme...

Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework

With the rise in use of social media to promote branded products, the de...

Leveraging convergence behavior to balance conflicting tasks in multi-task learning

Multi-Task Learning is a learning paradigm that uses correlated tasks to...