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.
Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models
School of Mathematics and Computer Science, Institute of Business Administration(商业管理学院数学与计算机科学学院);Center for Research in Computer Vision, University of Central Florida(中佛罗里达大学计算机视觉研究中心);National University of Computer and Emerging Sciences(国家计算机与新兴科学大学)
Mitigating covariate shift in non-colocated data with learned parameter priors
Institute of Business Administration Karachi(卡拉奇工商管理学院);Habib University Karachi(卡拉奇哈比卜大学);National University of Computer and Emergings Sciences, Karachi(卡拉奇国立计算机与新兴科学大学)