Active Learning for Deep Detection Neural Networks

Hamed H. Aghdam, Abel Gonzalez-Garcia, Joost van de Weijer, Antonio M. Lopez; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 3672-3680

Abstract


The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Aghdam_2019_ICCV,
author = {Aghdam, Hamed H. and Gonzalez-Garcia, Abel and Weijer, Joost van de and Lopez, Antonio M.},
title = {Active Learning for Deep Detection Neural Networks},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}