GenGMM: Generalized Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation
This addresses domain adaptation for semantic segmentation in real-world scenarios with noisy or incomplete labels, which is an incremental improvement over methods assuming fully labeled source data.
The paper tackles the problem of domain adaptive semantic segmentation under realistic conditions where source and target data may have partial or noisy labels, introducing GenGMM to leverage weak or unlabeled data from both domains to narrow the gap, with experiments showing effectiveness.
Domain adaptive semantic segmentation is the task of generating precise and dense predictions for an unlabeled target domain using a model trained on a labeled source domain. While significant efforts have been devoted to improving unsupervised domain adaptation for this task, it is crucial to note that many models rely on a strong assumption that the source data is entirely and accurately labeled, while the target data is unlabeled. In real-world scenarios, however, we often encounter partially or noisy labeled data in source and target domains, referred to as Generalized Domain Adaptation (GDA). In such cases, we suggest leveraging weak or unlabeled data from both domains to narrow the gap between them, resulting in effective adaptation. We introduce the Generalized Gaussian-mixture-based (GenGMM) domain adaptation model, which harnesses the underlying data distribution in both domains to refine noisy weak and pseudo labels. The experiments demonstrate the effectiveness of our approach.