arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08801cs.CV
收藏

Learning to Combine:多源领域自适应的知识聚合

Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation

Shanghai Jiao Tong University(上海交通大学)

Hang Wang, Minghao Xu, Bingbing Ni, Wenjun Zhang

摘要:

与传统的单源领域自适应相比,将多源领域的知识转移到目标领域是一个更实际、更具有挑战性的任务。此外,模态的增加带来了更多的困难,在多个领域之间的特征分布对齐。为了缓解这些问题,我们提出了一个学习合并多源领域自适应(LtC-MSDA)框架,通过探索领域之间的相互作用。简单地说,就是在各个领域的原型上构建一个知识图谱,实现语义相邻的表示之间的信息传播。在此基础上,学习一个图模型,在相关原型的指导下预测查询样本。此外,我们设计了一个关系对齐损失(RAL),以促进类别的关系相互依赖的一致性和紧凑的功能,这提高了功能的类内不变性和类间的可分性。公共基准数据集上的综合结果表明,我们的方法优于现有的方法具有显着的利润率。我们的代码可在\url{https://github.com/ChrisAllenMing/LtC-MSDA}上获得

英文摘要:

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}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑