Authors:
Clemens-Alexander Brust
1
;
Christoph Käding
2
and
Joachim Denzler
2
Affiliations:
1
Computer Vision Group, Friedrich Schiller University Jena and Germany
;
2
Computer Vision Group, Friedrich Schiller University Jena, Germany, Michael Stifel Center Jena and Germany
Keyword(s):
Active Learning, Deep Learning, Object Detection, YOLO, Continuous Learning, Incremental Learning.
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).