Image Augmentation for Object Detection and Segmentation with Diffusion Models

Leon Useinov, Valeria Efimova, Sergey Muravyov

2024

Abstract

Training current state-of-the-art models for object detection and segmentation requires a lot of labeled data, which can be difficult to obtain. It is especially hard, when occurrence of an object of interest in a certain required environment is rare. To solve this problem we present a train-free augmentation technique that is based on a diffusion model, pretrained on a large dataset (more than 1 million images). In order to establish the effectiveness of our method and its modifications, experiments on small datasets (less than 500 training images) with YOLOv8 are conducted. We conclude that none of the proposed versions of the diffusion-based augmentation method are universal, however, each of them may be used to improve an object detection (and segmentation) model performance in certain scenarios. The code is publicly available: github.com/PnthrLeo/ diffusion-augmentation.

Paper Citation

in Harvard Style

Useinov L., Efimova V. and Muravyov S. (2024). Image Augmentation for Object Detection and Segmentation with Diffusion Models. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 812-820. DOI: 10.5220/0012474500003660

in Bibtex Style

@conference{visapp24,
author={Leon Useinov and Valeria Efimova and Sergey Muravyov},
title={Image Augmentation for Object Detection and Segmentation with Diffusion Models},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={812-820},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012474500003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Image Augmentation for Object Detection and Segmentation with Diffusion Models
SN - 978-989-758-679-8
AU - Useinov L.
AU - Efimova V.
AU - Muravyov S.
PY - 2024
SP - 812
EP - 820
DO - 10.5220/0012474500003660
PB - SciTePress