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

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.

arXiv commentAccepted to ICCV 2021. Code is available at https://github.com/sheepooo/PIT-Position-Invariant-Transform

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Semi-supervised semantic segmentation needs strong, varied perturbations
• Context-Aware Mixup for Domain Adaptive Semantic Segmentation
• SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
• Self-Adversarial Disentangling for Specific Domain Adaptation

Cited by in corpus (8)

• Context-Aware Mixup for Domain Adaptive Semantic Segmentation
• Instance-Aware Domain Generalization for Face Anti-Spoofing
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• Generative Domain Adaptation for Face Anti-Spoofing
• Rethinking Domain Generalization: Discriminability and Generalizability
• DGMamba: Domain Generalization via Generalized State Space Model
• Self-Adversarial Disentangling for Specific Domain Adaptation
• DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection