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

08/16/2021
by   Qiqi Gu, et al.
0

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.

READ FULL TEXT

page 1

page 5

page 6

page 12

page 13

research
04/18/2022

Unsupervised Contrastive Domain Adaptation for Semantic Segmentation

Semantic segmentation models struggle to generalize in the presence of d...
research
04/01/2022

An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection

Existing deep learning-based change detection methods try to elaborately...
research
09/07/2020

Channel-wise Alignment for Adaptive Object Detection

Generic object detection has been immensely promoted by the development ...
research
11/30/2021

TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation

Due to the difficulty of obtaining ground-truth labels, learning from vi...
research
05/03/2022

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

Cross domain object detection is a realistic and challenging task in the...
research
08/10/2023

DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting

Domain adaptation is commonly employed in crowd counting to bridge the d...
research
03/15/2017

Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

While humans easily recognize relations between data from different doma...

Please sign up or login with your details

Forgot password? Click here to reset