Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching
This addresses the problem of semantic ambiguity in point cloud segmentation for applications like autonomous driving, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles unsupervised domain adaptation for point cloud semantic segmentation by proposing a graph-based framework for local-level feature alignment, achieving state-of-the-art performance in synthetic-to-real and real-to-real scenarios.
Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the knowledge from the source domain to the target domain, which may cause the semantic ambiguity of the feature space. In this paper, we propose a graph-based framework to explore the local-level feature alignment between the two domains, which can reserve semantic discrimination during adaptation. Specifically, in order to extract local-level features, we first dynamically construct local feature graphs on both domains and build a memory bank with the graphs from the source domain. In particular, we use optimal transport to generate the graph matching pairs. Then, based on the assignment matrix, we can align the feature distributions between the two domains with the graph-based local feature loss. Furthermore, we consider the correlation between the features of different categories and formulate a category-guided contrastive loss to guide the segmentation model to learn discriminative features on the target domain. Extensive experiments on different synthetic-to-real and real-to-real domain adaptation scenarios demonstrate that our method can achieve state-of-the-art performance.