Contrastive Vicinal Space for Unsupervised Domain Adaptation
This addresses domain adaptation for machine learning models by mitigating inter-domain discrepancies and intra-domain confusion, though it is incremental as it builds on existing vicinal space methods.
The paper tackles the problem of equilibrium collapse of labels in unsupervised domain adaptation by proposing an instance-wise minimax strategy that minimizes entropy in vicinal spaces, achieving state-of-the-art performance on benchmarks like Office-31, Office-Home, VisDA-C, and PACS.
Recent unsupervised domain adaptation methods have utilized vicinal space between the source and target domains. However, the equilibrium collapse of labels, a problem 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 the stated problem. 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 public benchmarks, including Office-31, Office-Home, and VisDA-C, achieving state-of-the-art performances. We further show that our method outperforms the current state-of-the-art methods on PACS, which indicates that our instance-wise approach works well for multi-source domain adaptation as well. Code is available at https://github.com/NaJaeMin92/CoVi.