OVANet: One-vs-All Network for Universal Domain Adaptation
This addresses domain and category shifts in machine learning for practical applications, but it is incremental as it builds on existing UNDA methods.
The paper tackles the problem of Universal Domain Adaptation (UNDA) by proposing OVANet, which learns a threshold to reject unknown classes in the target domain without manual tuning, and it outperforms baselines by a large margin.
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unknown classes which are absent in the labeled source data but present in the unlabeled target data. Existing methods manually set a threshold to reject unknown samples based on validation or a pre-defined ratio of unknown samples, but this strategy is not practical. In this paper, we propose a method to learn the threshold using source samples and to adapt it to the target domain. Our idea is that a minimum inter-class distance in the source domain should be a good threshold to decide between known or unknown in the target. To learn the inter-and intra-class distance, we propose to train a one-vs-all classifier for each class using labeled source data. Then, we adapt the open-set classifier to the target domain by minimizing class entropy. The resulting framework is the simplest of all baselines of UNDA and is insensitive to the value of a hyper-parameter yet outperforms baselines with a large margin.