Utilizing vicinal space between the source and target domains is one of the recent unsupervised domain adaptation approaches. However, the problem of the equilibrium collapse of labels, where the source labels are dominant over the target labels in the predictions of vicinal instances, has never been addressed. In this paper, we propose an instance-wise minimax strategy that minimizes the entropy of high uncertainty instances in the vicinal space to tackle it. We divide the vicinal space into two subspaces through the solution of the minimax problem: contrastive space and consensus space. In the contrastive space, inter-domain discrepancy is mitigated by constraining instances to have contrastive views and labels, and the consensus space reduces the confusion between intra-domain categories. The effectiveness of our method is demonstrated on the public benchmarks, including Office-31, Office-Home, and VisDA-C, which achieve state-of-the-art performances. We further show that our method outperforms current state-of-the-art methods on PACS, which indicates our instance-wise approach works well for multi-source domain adaptation as well.
翻译:利用源与目标区域之间的振动空间是最近未受监督的领域适应方法之一。然而,标签的平衡崩溃问题从未得到解决,因为标签的源标签在昆虫情况预测中压倒目标标签。在本文件中,我们提出了一个实例式的微型模型战略,以最大限度地减少振动空间中高度不确定性案例的酶性以解决这一问题。我们通过解决微缩问题将振动空间分为两个子空间:对比空间和共识空间。在对比空间中,差异之间的部分差异通过限制使用对比观点和标签来缓解,而共识空间则减少内部类别之间的混淆。我们的方法的有效性体现在公共基准上,包括31办公室、Home办公室和VisDA-C,这些基准达到了最新绩效。我们进一步表明,我们的方法超过了目前PACS的状态方法,这表明我们从实例角度出发的方法在多源域的适应方面效果很好。