End-To-End Multi-Task Learning With Attention

Shikun Liu, Edward Johns, Andrew J. Davison; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1871-1880


We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with a soft-attention module for each task. These modules allow for learning of task-specific features from the global features, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be trained end-to-end and can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. We evaluate our approach on a variety of datasets, across both image-to-image predictions and image classification tasks. We show that our architecture is state-of-the-art in multi-task learning compared to existing methods, and is also less sensitive to various weighting schemes in the multi-task loss function. Code is available at https://github.com/lorenmt/mtan.

Related Material

author = {Liu, Shikun and Johns, Edward and Davison, Andrew J.},
title = {End-To-End Multi-Task Learning With Attention},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}