Can I read PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation on EtoBox?

PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation by Gu, Qiqi; Zhou, Qianyu; Xu, Minghao; Feng, Zhengyang; Cheng, Guangliang; Lu, Xuequan; Shi, Jianping; Ma, Lizhuang is a scholarly article available to read on EtoBox.

What is PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation about?

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 \textbf{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

Author

Gu, Qiqi; Zhou, Qianyu; Xu, Minghao; Feng, Zhengyang; Cheng, Guangliang; Lu, Xuequan; Shi, Jianping; Ma, Lizhuang

Published

2021

Language

EN