Adversarially Trained Object Detector for Unsupervised Domain Adaptation

TL;DR

This paper introduces an adversarial training approach for unsupervised domain adaptation in object detection, improving robustness and transferability of features across significantly shifted domains.

Contribution

It proposes a novel adversarial training method combined with feature alignment to enhance object detection performance under large domain shifts.

Findings

Improved mean average precision by up to 7.7% on benchmark datasets.

Further improvement of up to 11.8% when combining adversarial training with feature alignment.

Method is effective for large domain shifts but less so for small shifts.

Abstract

Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation costs in the field of object detection. In this study, we demonstrate that adversarial training in the source domain can be employed as a new approach for unsupervised domain adaptation. Specifically, we establish that adversarially trained detectors achieve improved detection performance in target domains that are significantly shifted from source domains. This phenomenon is attributed to the fact that adversarially trained detectors can be used to extract robust features that are in alignment with human perception and worth transferring across domains while discarding domain-specific non-robust features. In addition, we propose a method that combines adversarial training and feature alignment to ensure the improved alignment of robust features with the target domain. We conduct experiments on four benchmark datasets and confirm the effectiveness of our proposed approach on large domain shifts from real to artistic images. Compared to the baseline models, the adversarially trained detectors improve the mean average precision by up to 7.7%, and further by up to 11.8% when feature alignments are incorporated. Although our method degrades performance for small domain shifts, quantification of the domain shift based on the Frechet distance allows us to determine whether adversarial training should be conducted.