MAC: Multi-Scales Attention Cascade for Aerial Image Segmentation

Yubo Wang, Zhao Wang, Yuusuke Nakano, Katsuya Hasegawa, Hiroyuki Ishii, Jun Ohya

2024

Abstract

Unlike general semantic segmentation, aerial image segmentation has its own particular challenges, three of the most prominent of which are great object scale variation, the scattering of multiple tiny objects in a complex background and imbalance between foreground and background. Previous affinity learning-based methods introduced intractable background noise but lost key-point information due to the additional interaction between different level features in their Feature Pyramid Network (FPN) like structure, which caused inferior results.We argue that multi-scale information can be further exploited in each FPN level individually without cross-level interaction, then propose a Multi-scale Attention Cascade (MAC) model to leverage spatial local contextual information by using multiple sized non-overlapping window self-attention module, which mitigates the effect of complex and imbalanced background. Moreover, the multi-scale contextual cues are propagated in a cascade manner to tackle the large scale variation problem while extracting further details. Finally, a local channels attention is presented to achieve cross-channel interaction. Extensive experiments verify the effectiveness of MAC and demonstrate that the performance of MAC surpasses those of the stateof-the-art approaches by +2.2 mIoU and +3.1 mFscore on iSAID dataset, by +2.97 mIoU on ISPRS Vaihingen dataset. Code has been made available at https://github.com/EricBooob/Multi-scale-Attention-Cascade-forAerial-Image-Segmentation.

Paper Citation

in Harvard Style

Wang Y., Wang Z., Nakano Y., Hasegawa K., Ishii H. and Ohya J. (2024). MAC: Multi-Scales Attention Cascade for Aerial Image Segmentation. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 37-47. DOI: 10.5220/0012343500003654

in Bibtex Style

@conference{icpram24,
author={Yubo Wang and Zhao Wang and Yuusuke Nakano and Katsuya Hasegawa and Hiroyuki Ishii and Jun Ohya},
title={MAC: Multi-Scales Attention Cascade for Aerial Image Segmentation},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={37-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012343500003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - MAC: Multi-Scales Attention Cascade for Aerial Image Segmentation
SN - 978-989-758-684-2
AU - Wang Y.
AU - Wang Z.
AU - Nakano Y.
AU - Hasegawa K.
AU - Ishii H.
AU - Ohya J.
PY - 2024
SP - 37
EP - 47
DO - 10.5220/0012343500003654
PB - SciTePress