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

TL;DR

This paper introduces Multitask-CenterNet (MCN), an anchor-free multi-task learning model that efficiently handles diverse perception tasks like detection, segmentation, and pose estimation, often outperforming single-task networks in speed and size.

Contribution

The paper presents MCN, a novel multi-task network that effectively combines diverse perception tasks with improved efficiency and performance over separate single-task models.

Findings

MCN can perform multiple perception tasks simultaneously with high accuracy.

MCN reduces inference time and network size compared to separate single-task networks.

MCN maintains or exceeds the performance of individual task networks.

Abstract

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.