Abstract
Unsupervised multi-domain adaptation plays a key role in transfer learning by leveraging acquired rich source information from multiple source domains to solve target task from an unlabeled target domain. However, multiple source domains often contain much redundant or unrelated information which can harm transfer performance, especially when in massive-source domain settings. It is urgent to develop effective strategies for identifying and selecting the most transferable knowledge from massive source domains to address the target task. In this paper, we propose a multi-domain adaptation method named \underline{\textit{Auto}}nomous Source Knowledge \underline{\textit{S}}election (AutoS) to autonomosly select source training samples and models, enabling the prediction of target task using more relevant and transferable source information. The proposed method employs a density-driven selection strategy to choose source samples during training and to determine which source models should contribute to target prediction. Simulteneously, a pseudo-label enhancement module built on a pre-trained multimodal modal is employed to mitigate target label noise and improve self-supervision. Experiments on real-world datasets indicate the superiority of the proposed method.
Abstract (translated)
无监督多领域适应在迁移学习中扮演着关键角色，通过利用从多个源域获取的丰富信息来解决未标记目标域中的任务。然而，在大量源域的情况下，这些源域往往包含许多冗余或无关的信息，这可能会损害迁移性能，尤其是在大规模源域设置下。因此，迫切需要开发有效的策略，以识别和选择最能转移的知识来自大量的源域，以便处理目标任务。 在本文中，我们提出了一种名为“自主源知识选择”（AutoS）的多领域适应方法，该方法能够自动选择源训练样本和模型，从而使用更相关和可迁移的源信息进行目标任务预测。所提出的方法采用一种基于密度驱动的选择策略，在训练过程中挑选出最佳的源样本，并确定哪些源模型应当贡献于目标预测中。同时，我们还引入了一个建立在预训练多模态模型上的伪标签增强模块，以减轻目标标记噪声并改进自我监督。 实验结果表明，所提出的方法在真实数据集上具有优越性。
URL
https://arxiv.org/abs/2512.14710
