Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models

Samiha Mirza, Vuong Nguyen, Pranav Mantini, Shishir Shah

2024

Abstract

In the midst of the rapid integration of artificial intelligence (AI) into real world applications, one pressing challenge we confront is the phenomenon of model drift, wherein the performance of AI models gradually degrades over time, compromising their effectiveness in real-world, dynamic environments. Once identified, we need techniques for handling this drift to preserve the model performance and prevent further degradation. This study investigates two prominent quality aware strategies to combat model drift: data quality assessment and data conditioning based on prior model knowledge. The former leverages image quality assessment metrics to meticulously select high-quality training data, improving the model robustness, while the latter makes use of learned feature vectors from existing models to guide the selection of future data, aligning it with the model’s prior knowledge. Through comprehensive experimentation, this research aims to shed light on the efficacy of these approaches in enhancing the performance and reliability of semantic segmentation models, thereby contributing to the advancement of computer vision capabilities in real-world scenarios.

Paper Citation

in Harvard Style

Mirza S., Nguyen V., Mantini P. and Shah S. (2024). Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 333-341. DOI: 10.5220/0012316000003660

in Bibtex Style

@conference{visapp24,
author={Samiha Mirza and Vuong Nguyen and Pranav Mantini and Shishir Shah},
title={Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={333-341},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012316000003660},
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 3: VISAPP
TI - Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models
SN - 978-989-758-679-8
AU - Mirza S.
AU - Nguyen V.
AU - Mantini P.
AU - Shah S.
PY - 2024
SP - 333
EP - 341
DO - 10.5220/0012316000003660
PB - SciTePress