# AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving

## TL;DR

This paper introduces AuxNet, a multi-task learning approach that leverages auxiliary tasks like depth estimation to enhance semantic segmentation accuracy in automated driving, using adaptive loss weighting.

## Contribution

It proposes adaptive task loss weighting techniques for multi-task learning, improving semantic segmentation performance without relying solely on synthetic datasets.

## Key findings

- Achieved 3% accuracy improvement on SYNTHIA dataset.
- Achieved 5% accuracy improvement on KITTI dataset.
- Demonstrated effectiveness of auxiliary tasks in real automotive datasets.

## Abstract

Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a challenging task which is now becoming mature to be productized in a car. However, semantic annotation is time consuming and quite expensive. Synthetic datasets with domain adaptation techniques have been used to alleviate the lack of large annotated datasets. In this work, we explore an alternate approach of leveraging the annotations of other tasks to improve semantic segmentation. Recently, multi-task learning became a popular paradigm in automated driving which demonstrates joint learning of multiple tasks improves overall performance of each tasks. Motivated by this, we use auxiliary tasks like depth estimation to improve the performance of semantic segmentation task. We propose adaptive task loss weighting techniques to address scale issues in multi-task loss functions which become more crucial in auxiliary tasks. We experimented on automotive datasets including SYNTHIA and KITTI and obtained 3% and 5% improvement in accuracy respectively.