Active learning for deep detection neural networks

Hamed Habibi Aghdam, Abel Gonzales-Garcia, Antonio M. Lopez, Joost van de Weijer

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

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. © 2019 IEEE.
Original languageEnglish
Title of host publication17th IEEE/CVF International Conference on Computer Vision
Pages3671-3679
Publication statusPublished - 2019

Cite this