Papers › Unsupervised domain adaptation using feature aligned maximum classifier discrepancy

Unsupervised domain adaptation using feature aligned maximum classifier discrepancy

3 Oct 2022Applications of Machine Learning, SPIE 2022 10archive 2025-07-28

Prasanna Reddy Pulakurthi, Sohail A. Dianat, Majid Rabbani, Suya You, Raghuveer M. Rao

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationUnsupervised Domain Adaptationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation MNIST-to-USPS FAMCD Accuracy 98.72 #2 of 14 Archive leaderboard report
Domain Adaptation SVHN-to-MNIST FAMCD Accuracy 98.76 #4 of 14 Archive leaderboard report
Domain Adaptation USPS-to-MNIST FAMCD Accuracy 98.75 #1 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections