Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 10133-10144


Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. On the other hand, most existing research was conducted under a supervised learning setup whereas 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.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Huang_2021_CVPR, author = {Huang, Jiaxing and Guan, Dayan and Xiao, Aoran and Lu, Shijian}, title = {Cross-View Regularization for Domain Adaptive Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {10133-10144} }