Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation


  • Minsu Kim Yonsei University
  • Sunghun Joung Yonsei University
  • Seungryong Kim Korea University
  • JungIn Park Yonsei University
  • Ig-Jae Kim KIST
  • Kwanghoon Sohn Yonsei University



Segmentation, Scene Analysis & Understanding, Adversarial Learning & Robustness, Transfer/Adaptation/Multi-task/Meta/Automated Learning


Existing techniques to adapt semantic segmentation networks across source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do not consider an inter-class variation within the target domain itself or estimated category, providing the limitation to encode the domains having a multi-modal data distribution. To overcome this limitation, we introduce a learnable clustering module, and a novel domain adaptation framework, called cross-domain grouping and alignment. To cluster the samples across domains with an aim to maximize the domain alignment without forgetting precise segmentation ability on the source domain, we present two loss functions, in particular, for encouraging semantic consistency and orthogonality among the clusters. We also present a loss so as to solve a class imbalance problem, which is the other limitation of the previous methods. Our experiments show that our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.




How to Cite

Kim, M., Joung, S., Kim, S., Park, J., Kim, I.-J., & Sohn, K. (2021). Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 1799-1807.



AAAI Technical Track on Computer Vision II