PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The maximum classifier discrepancy method has achieved great success in solving unsupervised domain adaptation tasks for image classification in recent years. Its basic structure consists of a feature generator and two classifiers that aim to maximize the classifier discrepancy while minimizing the generator discrepancy of the target samples. This method improves the performance of the existing adversarial training methods by employing task-specific classifiers that remove the ambiguity in classifying the target samples near the class boundaries. In this paper, we propose a modified network architecture and two training objectives to further boost the performance of the maximum classifier discrepancy method. The first training objective minimizes the feature level discrepancy and forces the generator to generate domain invariant features. This training objective is particularly beneficial when the source and the target domain distributions are vastly different. The second training objective that works at the mini-batch level aims at creating a uniform distribution of the target class predictions by maximizing the entropy of the expectation of the target class predictions. We show through extensive empirical evaluations that the proposed architecture and training objectives significantly improve the performance of the original algorithm. Furthermore, this method also outperforms the state-of-the-art techniques in most unsupervised domain adaptation tasks.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Prasanna Reddy Pulakurthi, Sohail A. Dianat, Majid Rabbani, Suya You, Raghuveer M. Rao, "Unsupervised domain adaptation using feature aligned maximum classifier discrepancy," Proc. SPIE 12227, Applications of Machine Learning 2022, 1222707 (3 October 2022); https://doi.org/10.1117/12.2646422