HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation
This addresses domain shift in deep learning for improved classification when training and test data distributions differ, though it appears incremental as it builds on existing SSDA methods.
The paper tackled the problem of semi-supervised domain adaptation by introducing HiGDA, a hierarchical graph method that learns local-to-global topology, achieving new state-of-the-art results on benchmark datasets like Office-Home, DomainNet, and VisDA2017.
The enhanced representational power and broad applicability of deep learning models have attracted significant interest from the research community in recent years. However, these models often struggle to perform effectively under domain shift conditions, where the training data (the source domain) is related to but exhibits different distributions from the testing data (the target domain). To address this challenge, previous studies have attempted to reduce the domain gap between source and target data by incorporating a few labeled target samples during training - a technique known as semi-supervised domain adaptation (SSDA). While this strategy has demonstrated notable improvements in classification performance, the network architectures used in these approaches primarily focus on exploiting the features of individual images, leaving room for improvement in capturing rich representations. In this study, we introduce a Hierarchical Graph of Nodes designed to simultaneously present representations at both feature and category levels. At the feature level, we introduce a local graph to identify the most relevant patches within an image, facilitating adaptability to defined main object representations. At the category level, we employ a global graph to aggregate the features from samples within the same category, thereby enriching overall representations. Extensive experiments on widely used SSDA benchmark datasets, including Office-Home, DomainNet, and VisDA2017, demonstrate that both quantitative and qualitative results substantiate the effectiveness of HiGDA, establishing it as a new state-of-the-art method.