Boomda：多模态域自适应的平衡多目标优化
Boomda: Balanced Multi-objective Optimization for Multimodal Domain Adaptation
AI总结：
针对多模态域自适应中标注数据稀缺、不同模态域偏移各异的问题，提出Boomda方法，通过信息瓶颈学习模态表示、相关性对齐匹配域并以多目标优化平衡对齐，实验表明其性能优于现有方案。
摘要：
多模态学习虽在各领域取得诸多成功，但面临手动标注成本过高的挑战。为解决标注数据稀缺问题，无监督域自适应是常用方案，其在单模态场景中已被广泛研究，但在多模态场景中仍较少探索。本文研究异构多模态域自适应，主要挑战是不同模态从源域到目标域的域偏移程度各异。我们首先引入信息瓶颈方法独立学习每个模态的表示，然后通过相关性对齐在表示空间中匹配源域和目标域。为平衡所有模态的域对齐，我们将该问题表述为多目标任务，旨在寻求帕累托最优解。通过利用模型的特定属性，该问题可简化为二次规划问题，进一步近似得到闭式解，从而形成高效的模态平衡多模态域自适应算法。所提方法具有多模态域自适应的平衡多目标优化特性，命名为Boomda。大量实验结果证明了所提方法的有效性，并表明Boomda优于现有竞争方案。代码可在https://github.com/sunjunaimer/Boomda.git获取。
英文摘要：
Multimodal learning, while contributing to numerous success stories across various fields, faces the challenge of prohibitively expensive manual annotation. To address the scarcity of annotated data, a popular solution is unsupervised domain adaptation, which has been extensively studied in unimodal settings yet remains less explored in multimodal settings. In this paper, we investigate heterogeneous multimodal domain adaptation, where the primary challenge is the varying domain shifts of different modalities from the source to the target domain. We first introduce the information bottleneck method to learn representations for each modality independently, and then match the source and target domains in the representation space with correlation alignment. To balance the domain alignment of all modalities, we formulate the problem as a multi-objective task, aiming for a Pareto optimal solution. By exploiting the properties specific to our model, the problem can be simplified to a quadratic programming problem. Further approximation yields a closed-form solution, leading to an efficient modality-balanced multimodal domain adaptation algorithm. The proposed method features \textbf{B}alanced multi-\textbf{o}bjective \textbf{o}ptimization for \textbf{m}ultimodal \textbf{d}omain \textbf{a}daptation, termed \textbf{Boomda}. Extensive empirical results showcase the effectiveness of the proposed approach and demonstrate that Boomda outperforms the competing schemes. The code is is available at: https://github.com/sunjunaimer/Boomda.git.
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。
