Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

被引:2
作者
Zhao, Zhen [1 ]
Guo, Yuhong [1 ,2 ]
Ye, Jieping [1 ]
机构
[1] DiDi Chuxing, Beijing, Peoples R China
[2] Carleton Univ, Ottawa, ON, Canada
来源
COMPUTER VISION - ECCV 2020 WORKSHOPS, PT I | 2020年 / 12535卷
关键词
Domain adaptation; Object detection; Style; Attention;
D O I
10.1007/978-3-030-66415-2_46
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection by performing cross-domain feature alignment in two dimensions, the depth dimension and the spatial dimension. In the depth dimension of channel layers, it uses inter-channel information to bridge the domain divergence with respect to image style alignment. In the dimension of spatial layers, it deploys spatial attention modules to enhance detection relevant regions and suppress irrelevant regions with respect to cross-domain feature alignment. Experiments are conducted on a number of benchmark cross-domain detection datasets. The empirical results show the proposed method outperforms the state-of-the-art comparison methods.
引用
收藏
页码:671 / 686
页数:16
相关论文
共 38 条
[1]   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
[2]   Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation [J].
Choi, Jaehoon ;
Kim, Taekyung ;
Kim, Changick .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :6829-6839
[3]  
Cicek S, 2019, Arxiv, DOI arXiv:1905.10885
[4]   The Cityscapes Dataset for Semantic Urban Scene Understanding [J].
Cordts, Marius ;
Omran, Mohamed ;
Ramos, Sebastian ;
Rehfeld, Timo ;
Enzweiler, Markus ;
Benenson, Rodrigo ;
Franke, Uwe ;
Roth, Stefan ;
Schiele, Bernt .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3213-3223
[5]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[6]  
Dziugaite GK, 2015, UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, P258
[7]   Object Detection with Discriminatively Trained Part-Based Models [J].
Felzenszwalb, Pedro F. ;
Girshick, Ross B. ;
McAllester, David ;
Ramanan, Deva .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (09) :1627-1645
[8]  
Ganin Y, 2016, J MACH LEARN RES, V17
[9]   Image Style Transfer Using Convolutional Neural Networks [J].
Gatys, Leon A. ;
Ecker, Alexander S. ;
Bethge, Matthias .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2414-2423
[10]  
Geiger A, 2012, PROC CVPR IEEE, P3354, DOI 10.1109/CVPR.2012.6248074