Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

TL;DR

This paper introduces a novel unsupervised cross-domain object detection method that aligns features in both depth and spatial dimensions to improve detection performance across different domains.

Contribution

It proposes a dual-dimensional feature alignment approach using inter-channel information and spatial attention modules, advancing cross-domain object detection techniques.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effective in reducing cross-domain feature divergence

Enhances detection accuracy in target domains

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.