A General Two-branch Decoder Architecture for Improving Encoder-decoder Image Segmentation Models

Sijie Hu, Fabien Bonardi, Samia Bouchafa, Désiré Sidibé

2022

Abstract

Recently, many methods with complex structures were proposed to address image parsing tasks such as image segmentation. These well-designed structures are hardly to be used flexibly and require a heavy footprint. This paper focuses on a popular semantic segmentation framework known as encoder-decoder, and points out a phenomenon that existing decoders do not fully integrate the information extracted by the encoder. To alleviate this issue, we propose a more general two-branch paradigm, composed of a main branch and an auxiliary branch, without increasing the number of parameters, and a boundary enhanced loss computation strategy to make two-branch decoders learn complementary information adaptively instead of explicitly indicating the specific learning element. In addition, one branch learn pixels that are difficult to resolve in another branch making a competition between them, which promotes the model to learn more efficiently. We evaluate our approach on two challenging image segmentation datasets and show its superior performance in different baseline models. We also perform an ablation study to tease apart the effects of different settings. Finally, we show our two-branch paradigm can achieve satisfactory results when remove the auxiliary branch in the inference stage, so that it can be applied to low-resource systems.

Paper Citation

in Harvard Style

Hu S., Bonardi F., Bouchafa S. and Sidibé D. (2022). A General Two-branch Decoder Architecture for Improving Encoder-decoder Image Segmentation Models. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 374-381. DOI: 10.5220/0010818800003124

in Bibtex Style

@conference{visapp22,
author={Sijie Hu and Fabien Bonardi and Samia Bouchafa and Désiré Sidibé},
title={A General Two-branch Decoder Architecture for Improving Encoder-decoder Image Segmentation Models},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={374-381},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010818800003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - A General Two-branch Decoder Architecture for Improving Encoder-decoder Image Segmentation Models
SN - 978-989-758-555-5
AU - Hu S.
AU - Bonardi F.
AU - Bouchafa S.
AU - Sidibé D.
PY - 2022
SP - 374
EP - 381
DO - 10.5220/0010818800003124
PB - SciTePress