English

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

Computer Vision and Pattern Recognition 2020-11-17 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2011.07205,
  title  = {Bi-Dimensional Feature Alignment for Cross-Domain Object Detection},
  author = {Zhen Zhao and Yuhong Guo and Jieping Ye},
  journal= {arXiv preprint arXiv:2011.07205},
  year   = {2020}
}

Comments

ECCV20 TASK-CV Workshop

R2 v1 2026-06-23T20:12:30.772Z