Active Learning for Deep Object Detection

Clemens-Alexander Brust, Christoph Käding, Joachim Denzler

2019

Abstract

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme (Käding et al., 2016b) to enable continuous exploration of new unlabeled datasets. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset (Everingham et al., 2010).

Download


Paper Citation


in Harvard Style

Brust C., Käding C. and Denzler J. (2019). Active Learning for Deep Object Detection. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 181-190. DOI: 10.5220/0007248601810190


in Bibtex Style

@conference{visapp19,
author={Clemens-Alexander Brust and Christoph Käding and Joachim Denzler},
title={Active Learning for Deep Object Detection},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={181-190},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007248601810190},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Active Learning for Deep Object Detection
SN - 978-989-758-354-4
AU - Brust C.
AU - Käding C.
AU - Denzler J.
PY - 2019
SP - 181
EP - 190
DO - 10.5220/0007248601810190
PB - SciTePress