AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

Sumanth Chennupati, Ganesh Sistu, Senthil Yogamani, Samir Rawashdeh

2019

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.

Paper Citation

in Harvard Style

Chennupati S., Sistu G., Yogamani S. and Rawashdeh S. (2019). AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 645-652. DOI: 10.5220/0007684106450652

in Bibtex Style

@conference{visapp19,
author={Sumanth Chennupati and Ganesh Sistu and Senthil Yogamani and Samir Rawashdeh},
title={AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={645-652},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007684106450652},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving
SN - 978-989-758-354-4
AU - Chennupati S.
AU - Sistu G.
AU - Yogamani S.
AU - Rawashdeh S.
PY - 2019
SP - 645
EP - 652
DO - 10.5220/0007684106450652
PB - SciTePress