SynFine: Boosting Image Segmentation Accuracy Through Synthetic Data Generation and Surgical Fine-Tuning

Mehdi Mounsif, Yassine Motie, Mohamed Benabdelkrim, Florent Brondolo

2023

Abstract

Carbon Capture and Storage (CCS) has increasingly been suggested as one of the many ways to reduce CO2 concentration in the atmosphere, hence tackling climate change and its consequences. As CCS involves robust modelling of physico-chemical mechanisms in geological formations, it benefits from CT-scans and accurate segmentation of rock core samples. Nevertheless, identifying precisely the components of a rock formation can prove challenging and could benefit from modern segmentation approaches, such as U-Net. In this context, this work introduces SynFine, a framework that relies on synthetic data generation and surgical fine-tuning to boost the performance of a model on a target data distribution with a limited number of examples. Specifically, after a pre-training phase on a source dataset, the SynFine approach identifies and fine-tunes the most responsive layers regarding the distribution shift. Our experiments show that, beyond an advantageous final performance, SynFine enables a strong reduction of the number of real-world labelled pairs for a given level of performance.

Paper Citation

in Harvard Style

Mounsif M., Motie Y., Benabdelkrim M. and Brondolo F. (2023). SynFine: Boosting Image Segmentation Accuracy Through Synthetic Data Generation and Surgical Fine-Tuning. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 565-573. DOI: 10.5220/0011848300003411

in Bibtex Style

@conference{icpram23,
author={Mehdi Mounsif and Yassine Motie and Mohamed Benabdelkrim and Florent Brondolo},
title={SynFine: Boosting Image Segmentation Accuracy Through Synthetic Data Generation and Surgical Fine-Tuning},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={565-573},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011848300003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - SynFine: Boosting Image Segmentation Accuracy Through Synthetic Data Generation and Surgical Fine-Tuning
SN - 978-989-758-626-2
AU - Mounsif M.
AU - Motie Y.
AU - Benabdelkrim M.
AU - Brondolo F.
PY - 2023
SP - 565
EP - 573
DO - 10.5220/0011848300003411