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.
翻译:未经监督的域适应包括将知识从标签丰富源域转移到未加标记的目标域域,这涉及到将知识从标签丰富源域转移到未加标记的目标域域,可以用来大大减少物体探测领域的批注费用。在本研究中,我们证明源域的对抗性培训可以作为未受监督域适应的新办法加以使用。具体地说,我们确定,经过对抗性培训的探测器在目标域从来源域向艺术域大幅转移的目标域中提高了探测性能。这个现象的原因在于,经过对抗性对抗性训练的探测器可以用来提取与人类感知一致、值得跨域转移的稳健性特征,同时抛弃特定域非紫外特性。此外,我们建议一种方法,将对抗性培训和特征调整结合起来,以确保强性特征与目标域更趋一致。我们在四个基准数据集上进行实验,并确认我们提议的大域从真实图像向艺术域大变换的方法的有效性。与基线模型相比,经过对抗性训练的探测器可以提高平均精确度,最高为7.7%,在纳入特性校准功能调整时,最高为11.8%。虽然我们的方法降解法变的域域域域内,是否进行远距离测算。