CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning

TL;DR

CERBERUS is a lightweight multitask deep learning model designed for automotive perception, capable of performing multiple tasks simultaneously on embedded platforms, reducing computational load while maintaining high performance.

Contribution

This work introduces CERBERUS, a novel all-in-one perception model that combines multiple automotive perception tasks into a single efficient network using multitask learning.

Findings

Achieves competitive accuracy across perception tasks

Reduces computational requirements for embedded systems

Demonstrates effective multitask learning in automotive perception

Abstract

Perceiving the surrounding environment is essential for enabling autonomous or assisted driving functionalities. Common tasks in this domain include detecting road users, as well as determining lane boundaries and classifying driving conditions. Over the last few years, a large variety of powerful Deep Learning models have been proposed to address individual tasks of camera-based automotive perception with astonishing performances. However, the limited capabilities of in-vehicle embedded computing platforms cannot cope with the computational effort required to run a heavy model for each individual task. In this work, we present CERBERUS (CEnteR Based End-to-end peRception Using a Single model), a lightweight model that leverages a multitask-learning approach to enable the execution of multiple perception tasks at the cost of a single inference. The code will be made publicly available at https://github.com/cscribano/CERBERUS