GenGMM: Generalized Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation

TL;DR

GenGMM introduces a novel domain adaptation model for semantic segmentation that leverages data distributions to improve adaptation in scenarios with noisy or weak labels in both source and target domains.

Contribution

It proposes the GenGMM model that utilizes Gaussian mixture models to refine labels and adapt across domains with noisy or partial annotations, addressing real-world challenges.

Findings

Effective in handling noisy and weak labels in both domains

Improves segmentation accuracy in generalized domain adaptation scenarios

Outperforms existing methods on benchmark datasets

Abstract

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.