论文标题
学习结合：多源域适应的知识汇总
Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
论文作者
论文摘要
从多个源域到目标域中学到的转移知识比传统的单源域的适应性更实用，更具挑战性。此外，模式的增加在对齐多个域之间的特征分布方面更加困难。为了减轻这些问题，我们建议通过探索域之间的相互作用来进行多源域适应（LTC-MSDA）框架的学习。简而言之，在各个领域的原型上构建了知识图，以实现语义相邻表示之间的信息传播。在这种基础上，学会了图形模型来预测相关原型的指导下的查询样品。此外，我们设计了一个关系对准损失（RAL），以促进类别相互依存关系和特征的紧凑性的一致性，这增强了阶层内的不变性和类间的分离性。公共基准数据集的全面结果表明，我们的方法的表现优于现有方法，并具有显着的利润。我们的代码可在\ url {https://github.com/chrisallenming/ltc-msda}中找到
Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation. Furthermore, the increase of modalities brings more difficulty in aligning feature distributions among multiple domains. To mitigate these problems, we propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework via exploring interactions among domains. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations. On such basis, a graph model is learned to predict query samples under the guidance of correlated prototypes. In addition, we design a Relation Alignment Loss (RAL) to facilitate the consistency of categories' relational interdependency and the compactness of features, which boosts features' intra-class invariance and inter-class separability. Comprehensive results on public benchmark datasets demonstrate that our approach outperforms existing methods with a remarkable margin. Our code is available at \url{https://github.com/ChrisAllenMing/LtC-MSDA}
