Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation

TL;DR

This paper introduces an 'against adversarial learning' approach for open set domain adaptation, enabling models to naturally distinguish known from unknown target data without extra hyperparameters, improving performance over existing methods.

Contribution

The paper proposes a novel adversarial learning method that effectively separates known and unknown data in open set domain adaptation without additional hyperparameters.

Findings

Significant performance improvement over state-of-the-art methods

Effective distinction between known and unknown target data

No extra hyperparameters needed for the method

Abstract

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.