Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requires distinguishing the unknown samples from the known ones in the target domain. A main challenge of UniDA is that the nonidentical label sets cause the misalignment between the two domains. Moreover, the domain discrepancy and the supervised objectives in the source domain easily lead the whole model to be biased towards the common classes and produce overconfident predictions for unknown samples. To address the above challenging problems, we propose a new uncertainty-guided UniDA framework. Firstly, we introduce an empirical estimation of the probability of a target sample belonging to the unknown class which fully exploits the distribution of the target samples in the latent space. Then, based on the estimation, we propose a novel neighbors searching scheme in a linear subspace with a $\delta$-filter to estimate the uncertainty score of a target sample and discover unknown samples. It fully utilizes the relationship between a target sample and its neighbors in the source domain to avoid the influence of domain misalignment. Secondly, this paper well balances the confidences of predictions for both known and unknown samples through an uncertainty-guided margin loss based on the confidences of discovered unknown samples, which can reduce the gap between the intra-class variances of known classes with respect to the unknown class. Finally, experiments on three public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.
翻译:通用领域自适应(UniDA)旨在在没有标签集假设的情况下,将标注源域的知识转移到无标注目标域,这需要区分目标域中的未知样本和已知样本。UniDA的主要挑战是非相同的标签集导致两个域之间的不匹配。此外,源域中的领域差异和监督目标很容易使得整个模型偏向于通用类别,并对未知样本产生过度自信的预测。为了解决以上挑战性问题,我们提出了一种新的不确定性导向的UniDA框架。首先,我们引入了目标样本属于未知类别的机率的经验估计,这充分利用了潜在空间中目标样本的分布。接着,基于这个估计,我们提出了一种在线性子空间中带有$\delta$-过滤的邻居搜索方案,以估计目标样本的不确定性分数和发现未知样本。它充分利用了目标样本和它在源域中的邻居之间的关系,避免了领域不匹配的影响。其次,本文通过根据发现的未知样本的信心值,在不确定性引导的边缘损失基础上,很好地平衡了已知和未知样本的预测置信度,它可以减少已知类与未知类的类内方差之间的差距。最后,在三个公共数据集上进行的实验表明,我们的方法显著优于现有的最先进方法。