Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection

Tobias Riedlinger, Marius Schubert, Karsten Kahl, Hanno Gottschalk, Matthias Rottmann

2024

Abstract

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods in such fields is highly computationally expensive and time consuming which obstructs the progression of research and leads to a lack of comparability between methods. In this work, we propose and investigate a sandbox setup for rapid development and transparent evaluation of active learning in deep object detection. Our experiments with commonly used configurations of datasets and detection architectures found in the literature show that results obtained in our sandbox environment are representative of results on standard configurations. The total compute time to obtain results and assess the learning behavior can be reduced by factors of up to 14 compared to Pascal VOC and up to 32 compared to BDD100k. This allows for testing and evaluating data acquisition and labeling strategies in under half a day and contributes to the transparency and development speed in the field of active learning for object detection.

Paper Citation

in Harvard Style

Riedlinger T., Schubert M., Kahl K., Gottschalk H. and Rottmann M. (2024). Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection. 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 366-374. DOI: 10.5220/0012315400003660

in Bibtex Style

@conference{visapp24,
author={Tobias Riedlinger and Marius Schubert and Karsten Kahl and Hanno Gottschalk and Matthias Rottmann},
title={Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={366-374},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012315400003660},
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 - Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection
SN - 978-989-758-679-8
AU - Riedlinger T.
AU - Schubert M.
AU - Kahl K.
AU - Gottschalk H.
AU - Rottmann M.
PY - 2024
SP - 366
EP - 374
DO - 10.5220/0012315400003660
PB - SciTePress