TY  - CONF
AU  - Hamed H. Aghdam
AU  - Abel Gonzalez-Garcia
AU  - Joost Van de Weijer
AU  - Antonio Lopez
A2  - ICCV
PY  - 2019//
TI  - Active Learning for Deep Detection Neural Networks
BT  - 18th IEEE International Conference on Computer Vision
SP  - 3672
EP  - 3680
N2  - The cost of drawing object bounding boxes (ie 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.
UR  - https://ieeexplore.ieee.org/document/9009535
L1  - http://refbase.cvc.uab.es/files/AGW2019.pdf
UR  - http://dx.doi.org/10.1109/ICCV.2019.00377
N1  - ADAS; LAMP; 600.124; 600.109; 600.141; 600.120; 600.118
ID  - Hamed H. Aghdam2019
ER  -