Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

05/19/2017
by   Alex Kendall, et al.
0

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.

READ FULL TEXT

page 8

page 12

page 13

research
05/09/2020

Multi-Task Learning in Histo-pathology for Widely Generalizable Model

In this work we show preliminary results of deep multi-task learning in ...
research
04/15/2019

MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning

Multi-task learning is commonly used in autonomous driving for solving v...
research
07/01/2020

Multi-Task Variational Information Bottleneck

In this paper we propose a multi-task deep learning model called multi-t...
research
05/22/2018

Infinite-Task Learning with Vector-Valued RKHSs

Machine learning has witnessed the tremendous success of solving tasks d...
research
08/26/2020

HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks

Multi-task learning (MTL) can improve performance on a task by sharing r...
research
10/28/2020

Polymer Informatics with Multi-Task Learning

Modern data-driven tools are transforming application-specific polymer d...
research
03/06/2022

On Steering Multi-Annotations per Sample for Multi-Task Learning

The study of multi-task learning has drawn great attention from the comm...

Please sign up or login with your details

Forgot password? Click here to reset