Mixing Augmentation and Knowledge-Based Techniques in Unsupervised Domain Adaptation for Segmentation of Edible Insect States

Paweł Majewski, Piotr Lampa, Robert Burduk, Jacek Reiner

2023

Abstract

Models for detecting edible insect states (live larvae, dead larvae, pupae) are a crucial component of large-scale edible insect monitoring systems. The problem of changing the nature of the data (domain shift) that occurs when implementing the system to new conditions results in a reduction in the effectiveness of previously developed models. Proposing methods for the unsupervised adaptation of models is necessary to reduce the adaptation time of the entire system to new breeding conditions. The study acquired images from three data sources characterized by different types of cameras and illumination and checked the inference quality of the model trained in the source domain on samples from the target domain. A hybrid approach based on mixing augmentation and knowledge-based techniques was proposed to adapt the model. The first stage of the proposed method based on object augmentation and synthetic image generation enabled an increase in average AP50 from 58.4 to 62.9. The second stage of the proposed method, based on knowledge-based filtering of target domain objects and synthetic image generation, enabled a further increase in average AP50 from 62.9 to 71.8. The strategy of mixing objects from the source domain and the target domain (AP50=71.8) when generating synthetic images proved to be much better than the strategy of using only objects from the target domain (AP50=65.5). The results show the great importance of augmentation and a priori knowledge when adapting models to a new domain.

Paper Citation

in Harvard Style

Majewski P., Lampa P., Burduk R. and Reiner J. (2023). Mixing Augmentation and Knowledge-Based Techniques in Unsupervised Domain Adaptation for Segmentation of Edible Insect States. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 380-387. DOI: 10.5220/0011603500003417

in Bibtex Style

@conference{visapp23,
author={Paweł Majewski and Piotr Lampa and Robert Burduk and Jacek Reiner},
title={Mixing Augmentation and Knowledge-Based Techniques in Unsupervised Domain Adaptation for Segmentation of Edible Insect States},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={380-387},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011603500003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Mixing Augmentation and Knowledge-Based Techniques in Unsupervised Domain Adaptation for Segmentation of Edible Insect States
SN - 978-989-758-634-7
AU - Majewski P.
AU - Lampa P.
AU - Burduk R.
AU - Reiner J.
PY - 2023
SP - 380
EP - 387
DO - 10.5220/0011603500003417
PB - SciTePress