Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation
This addresses a common real-world scenario in domain adaptation for machine learning, offering a practical solution for distinguishing unknown classes, though it appears incremental in its approach.
The paper tackles the problem of open set domain adaptation, where target domains contain unknown categories not present in the source, by proposing an 'against adversarial learning' method that naturally distinguishes known and unknown data without extra hyperparameters. Experimental results show it significantly outperforms state-of-the-art methods.
Open set domain adaptation refers to the scenario that the target domain contains categories that do not exist in the source domain. It is a more common situation in the reality compared with the typical closed set domain adaptation where the source domain and the target domain contain the same categories. The main difficulty of open set domain adaptation is that we need to distinguish which target data belongs to the unknown classes when machine learning models only have concepts about what they know. In this paper, we propose an "against adversarial learning" method that can distinguish unknown target data and known data naturally without setting any additional hyper parameters and the target data predicted to the known classes can be classified at the same time. Experimental results show that the proposed method can make significant improvement in performance compared with several state-of-the-art methods.