Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

14 Nov 2020  ·  Zhen Zhao, Yuhong Guo, Jieping Ye ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Unsupervised Domain Adaptation Cityscapes to Foggy Cityscapes SSA-DA mAP@0.5 42.5 # 14
Image-to-Image Translation Cityscapes-to-Foggy Cityscapes SSA-DA mAP 42.5 # 2

Methods


No methods listed for this paper. Add relevant methods here