当前位置: X-MOL 学术Knowl. Based Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Incremental learning based multi-domain adaptation for object detection
Knowledge-Based Systems ( IF 8.8 ) Pub Date : 2020-09-18 , DOI: 10.1016/j.knosys.2020.106420
Xing Wei , Shaofan Liu , Yaoci Xiang , Zhangling Duan , Chong Zhao , Yang Lu

Cross-domain object detection uses knowledge from source domain tasks to enhance the object detection in target domain. It can reduce the workload of data annotations in the new domain and significantly improve the adaptation ability of the network. We consider a more realistic transfer scenario, that is, our target domain samples cannot be obtained at the same time so that learners cannot forget the old domain knowledge while learning the new domain knowledge, which is consistent with the basic assumption of incremental learning. However, the existing methods do not consider the sequential learning process of the multiple target domains which may cause performance degradation. To address this issue, we propose a novel multi-domain adaptation method for object detection based on incremental learning. Specifically, the incremental learning network saves the knowledge of multiple domains and makes the model to fuse the knowledge of different domains during the training effectively. To make it work better, the progressive training strategy is proposed to make the model gradually adapt to multiple domains. Moreover, we use a multi-level feature alignment module to ensure that domain alignment is realized on features at various levels. We perform experiments on two sets of 6 datasets, which demonstrate that our model can effectively solve the problem of domain knowledge forgetting in multi-target domain adaptation and significantly improve the detection accuracy in each domain.



中文翻译:

基于增量学习的多域自适应目标检测

跨域对象检测使用源域任务中的知识来增强目标域中的对象检测。它可以减少新领域中数据注释的工作量,并显着提高网络的适应能力。我们考虑了一种更现实的转移方案,即无法同时获取目标领域样本,以使学习者在学习新领域知识时不会忘记旧的领域知识,这与增量学习的基本假设是一致的。但是,现有方法没有考虑可能导致性能下降的多个目标域的顺序学习过程。为了解决这个问题,我们提出了一种新的基于增量学习的多域自适应目标检测方法。特别,增量学习网络可以节省多个领域的知识,并使模型在训练过程中有效融合不同领域的知识。为了使其更好地工作,提出了渐进式训练策略,以使模型逐渐适应多个领域。此外,我们使用多级特征对齐模块来确保在各个级别的要素上实现域对齐。我们对两组6个数据集进行了实验,证明我们的模型可以有效解决多目标领域自适应中的领域知识遗忘问题,并显着提高每个领域的检测准确性。提出了渐进式训练策略,以使模型逐渐适应多个领域。此外,我们使用多级特征对齐模块来确保在各个级别的要素上实现域对齐。我们对两组6个数据集进行了实验,证明我们的模型可以有效解决多目标领域自适应中的领域知识遗忘问题,并显着提高每个领域的检测准确性。提出了渐进式训练策略,使模型逐渐适应多个领域。此外,我们使用多级特征对齐模块来确保在各个级别的要素上实现域对齐。我们对两组6个数据集进行了实验,证明我们的模型可以有效解决多目标领域自适应中的领域知识遗忘问题,并显着提高每个领域的检测准确性。

更新日期:2020-10-04
down
wechat
bug