MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach

08/11/2021
by   Falk Heuer, et al.
37

Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved, while the objectives performance remains on a similar or even higher level. However, in perception related multitask networks only closely related tasks can be found, such as object detection, instance and semantic segmentation or depth estimation. Multitask networks with diverse tasks and their effects with respect to efficiency on one another are not well studied. In this paper we augment the CenterNet anchor-free approach for training multiple diverse perception related tasks together, including the task of object detection and semantic segmentation as well as human pose estimation. We refer to this DNN as Multitask-CenterNet (MCN). Additionally, we study different MCN settings for efficiency. The MCN can perform several tasks at once while maintaining, and in some cases even exceeding, the performance values of its corresponding single task networks. More importantly, the MCN architecture decreases inference time and reduces network size when compared to a composition of single task networks.

READ FULL TEXT

page 1

page 4

page 5

page 8

page 9

research
05/03/2022

Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring

In order to ensure safe autonomous driving, precise information about th...
research
10/31/2017

A multitask deep learning model for real-time deployment in embedded systems

We propose an approach to Multitask Learning (MTL) to make deep learning...
research
09/02/2018

Multitask Learning for Fundamental Frequency Estimation in Music

Fundamental frequency (f0) estimation from polyphonic music includes the...
research
04/05/2016

Deep Cross Residual Learning for Multitask Visual Recognition

Residual learning has recently surfaced as an effective means of constru...
research
01/07/2020

Multitask learning over graphs

The problem of learning simultaneously several related tasks has receive...
research
03/02/2017

Self-Paced Multitask Learning with Shared Knowledge

This paper introduces self-paced task selection to multitask learning, w...
research
12/04/2021

Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction

Multimodal fusion and multitask learning are two vital topics in machine...

Please sign up or login with your details

Forgot password? Click here to reset