PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation

Gu, Qiqi, Zhou, Qianyu, Xu, Minghao, Feng, Zhengyang, Cheng, Guangliang ORCID: 0000-0001-8686-9513, Lu, Xuequan, Shi, Jianping and Ma, Lizhuang (2021) PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021-10-10 - 2021-10-17.

Access the full-text of this item by clicking on the Open Access link.

Official URL: http://dx.doi.org/10.1109/iccv48922.2021.00864

Abstract

Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination or weather, while distinct camera intrinsic parameters appear commonly in different domains and their influence for domain adaptation has been very rarely explored. In this paper, we observe that the Field of View (FoV) gap induces noticeable instance appearance differences between the source and target domains. We further discover that the FoV gap between two domains impairs domain adaptation performance under both the FoV-increasing (source FoV < target FoV) and FoV-decreasing cases. Motivated by the observations, we propose the Position-Invariant Transform (PIT) to better align images in different domains. We also introduce a reverse PIT for mapping the transformed/aligned images back to the original image space, and design a loss re-weighting strategy to accelerate the training process. Our method can be easily plugged into existing cross-domain detection/segmentation frameworks, while bringing about negligible computational overhead. Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques. Our code is available at https://github.com/sheepooo/PIT-Position-Invariant-Transform.

Item Type:	Conference or Workshop Item (Unspecified)
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	14 Mar 2023 09:32
Last Modified:	24 Apr 2024 11:30
DOI:	10.1109/iccv48922.2021.00864
Open Access URL:	https://openaccess.thecvf.com/content/ICCV2021/pap...
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3168998