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

Source: [PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation](<https://www.sota2.com/research/paper/68fa6e091e209131cea3d8fc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:48:10.793Z

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

Published: 2021-08-16T15:16:47.000Z

## 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 \\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. 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.07142>)

[PDF](<https://arxiv.org/pdf/2108.07142.pdf>)
