Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

被引:138
作者
Kim, Seunghyeon [1 ]
Choi, Jaehoon [1 ]
Kim, Taekyung [1 ]
Kim, Changick [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea
来源
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年
关键词
D O I
10.1109/ICCV.2019.00619
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have different distributions. To address the issue, domain adaptation transfers knowledge from the label-sufficient domain (source domain) to the label-scarce domain (target domain). Self-training is one of the powerful ways to achieve domain adaptation since it helps class-wise domain adaptation. Unfortunately, a naive approach that utilizes pseudo-labels as ground-truth degenerates the performance due to incorrect pseudo-labels. In this paper, we introduce a weak self-training (WST) method and adversarial background score regularization (BSR) for domain adaptive one-stage object detection. WST diminishes the adverse effects of inaccurate pseudo-labels to stabilize the learning procedure. BSR helps the network extract discriminative features for target backgrounds to reduce the domain shift. Two components are complementary to each other as BSR enhances discrimination between foregrounds and backgrounds, whereas WST strengthen class-wise discrimination. Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting.
引用
收藏
页码:6091 / 6100
页数:10
相关论文
共 40 条
[1]  
[Anonymous], 2018, P ICML
[2]  
Chapelle O., 2009, Semi-Supervised Learning, V20, P542, DOI 10.1109/TNN.2009.2015974
[3]  
Chen M., 2011, ADV NEURAL INFORM PR, P2456, DOI DOI 10.1016/B978-012545025-6/50150-7
[4]   Domain Adaptive Faster R-CNN for Object Detection in the Wild [J].
Chen, Yuhua ;
Li, Wen ;
Sakaridis, Christos ;
Dai, Dengxin ;
Van Gool, Luc .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :3339-3348
[5]  
Chitta Kashyap, 2018, ARXIV181103542
[6]  
Choi J., 2019, P 30 BRIT MACH VIS C, P67
[7]  
Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036
[8]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[9]   The Pascal Visual Object Classes (VOC) Challenge [J].
Everingham, Mark ;
Van Gool, Luc ;
Williams, Christopher K. I. ;
Winn, John ;
Zisserman, Andrew .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 88 (02) :303-338
[10]  
French G., 2017, ARXIV170605208