TY - GEN
T1 - Missing labels in object detection
AU - Xu, Mengmeng
AU - Bai, Yancheng
AU - Ghanem, Bernard
N1 - Funding Information:
Acknowledgments This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research and by Natural Science Foundation of China, Grant No. 61603372.
Publisher Copyright:
© 2019 IEEE Computer Society. All rights reserved.
PY - 2019/6
Y1 - 2019/6
N2 - Object detection is a fundamental problem in computer vision. Impressive results have been achieved on large-scale detection benchmarks by fully-supervised object detection (FSOD) methods. However, FSOD performance is highly affected by the quality of annotations available in training. Furthermore, FSOD approaches require tremendous instance-level annotations, which are time-consuming to collect. In contrast, weakly supervised object detection (WSOD) exploits easily-collected image-level labels while it suffers from relatively inferior detection performance. In this paper, we study the effect of missing annotations on FSOD methods and analyze approaches to train an object detector from a hybrid dataset, where both instance-level and image-level labels are employed. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 benchmarks strongly demonstrate the effectiveness of our method, which gives a trade-off between collecting fewer annotations and building a more accurate object detector. Our method is also a strong baseline bridging the wide gap between FSOD and WSOD performances.
AB - Object detection is a fundamental problem in computer vision. Impressive results have been achieved on large-scale detection benchmarks by fully-supervised object detection (FSOD) methods. However, FSOD performance is highly affected by the quality of annotations available in training. Furthermore, FSOD approaches require tremendous instance-level annotations, which are time-consuming to collect. In contrast, weakly supervised object detection (WSOD) exploits easily-collected image-level labels while it suffers from relatively inferior detection performance. In this paper, we study the effect of missing annotations on FSOD methods and analyze approaches to train an object detector from a hybrid dataset, where both instance-level and image-level labels are employed. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 benchmarks strongly demonstrate the effectiveness of our method, which gives a trade-off between collecting fewer annotations and building a more accurate object detector. Our method is also a strong baseline bridging the wide gap between FSOD and WSOD performances.
UR - http://www.scopus.com/inward/record.url?scp=85111550820&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85111550820
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1
EP - 10
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 16 June 2019 through 20 June 2019
ER -