arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05294cs.CV
收藏

协变量与概念漂移下目标检测的域泛化

Domain Generalisation for Object Detection under Covariate and Concept Shift

Applied AGI Limited(应用AGI有限公司);Sabanci University(萨班哲大学);University of Lincoln(林肯大学)

Karthik Seemakurthy, Erchan Aptoula, Charles Fox, Petra Bosilj

AI总结:

提出首个可适配任意目标检测架构的域泛化方法,通过图像级边缘分布与实例级类别条件特征对齐,同时应对协变量漂移和概念漂移,并在多类检测器与跨领域基准上验证性能提升。

摘要:

域泛化旨在促进学习域不变特征,同时抑制域特定特征,从而使模型能够更好地泛化到此前未见的目标域。本文提出了一种用于目标检测的域泛化方法,这是首个适用于任意目标检测架构的此类方法。基于严谨的数学分析,我们扩展了基于特征对齐的方法:除了在图像级对齐跨域的边缘特征分布之外,还加入了一个新颖组件,用于在实例级执行类别条件对齐。这使我们能够完整应对域漂移的两个组成部分,即协变量漂移和概念漂移,并学习与域无关的特征表示。我们使用单阶段检测器(FCOS、YOLO)和两阶段检测器(FRCNN)进行了广泛评估;评估在一个新提出的基准上进行,该基准包含面向自动驾驶应用的多个不同数据集(Cityscapes、BDD10K、ACDC、IDD)以及用于精准农业的 GWHD 数据集。结果表明,相较基线方法和当前最先进方法,泛化性能与定位性能均获得持续提升。

英文摘要:

Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features, so that a model can generalise better to previously unseen target domains. An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture. Based on a rigorous mathematical analysis, we extend approaches based on feature alignment with a novel component for performing class conditional alignment at the instance level, in addition to aligning the marginal feature distributions across domains at the image level. This allows us to fully address both components of domain shift, i.e. covariate and concept shift, and learn a domain agnostic feature representation. We perform extensive evaluation with both one-stage (FCOS, YOLO) and two-stage (FRCNN) detectors, on a newly proposed benchmark comprising several different datasets for autonomous driving applications (Cityscapes, BDD10K, ACDC, IDD) as well as the GWHD dataset for precision agriculture, and show consistent improvements to the generalisation and localisation performance over baselines and state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑