Cross-View Regularization for Domain Adaptive Panoptic Segmentation
This addresses the problem of domain shift in panoptic segmentation for applications like autonomous driving, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackles unsupervised domain adaptive panoptic segmentation by designing a network that uses inter-style consistency and inter-task regularization to learn domain-invariant features, achieving superior performance compared to state-of-the-art methods in tasks like synthetic-to-real and real-to-real adaptation.
Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. However, most existing research was conducted under a supervised learning setup whereas unsupervised domain adaptive panoptic segmentation which is critical in different tasks and applications is largely neglected. We design a domain adaptive panoptic segmentation network that exploits inter-style consistency and inter-task regularization for optimal domain adaptive panoptic segmentation. The inter-style consistency leverages geometric invariance across the same image of the different styles which fabricates certain self-supervisions to guide the network to learn domain-invariant features. The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains. Extensive experiments over multiple domain adaptive panoptic segmentation tasks (e.g., synthetic-to-real and real-to-real) show that our proposed network achieves superior segmentation performance as compared with the state-of-the-art.