YuSeung Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
YuSeung Ma has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Erin Woo
Korea National University of Science and Technology
1 shared publication- Hyung Kook Jun
Sungkyunkwan University
1 shared publication - Sangyeop Yeo
Korea National University of Science and Technology
1 shared publication - Young Ik Eom
Sungkyunkwan University
1 shared publication
Latest Publications
- Open Access
- 1 September 2025
- Published by Springer Nature in Research Square
Classification Accuracy Estimation Without Labels via Architecture-Agnostic Model Agreement
We propose a method to estimate the classification accuracy of a machine learning model without requiring any ground-truth labels, by leveraging the agreement between two models on unlabeled data. Unlike prior work that interprets model agreement as an upper bound or average of model accuracies, we are the first to demonstrate that in heterogeneous, label-free settings, agreement reliably approximates the performance of the weaker model in the pair. Our method is architecture-agnostic and does not require any labeled data, assumptions on model calibration, or prior performance information. We introduce a principled estimator that combines hard-label agreement, probability-level consistency, and a correction term for class imbalance and calibration bias. This estimator remains robust across diverse model types—including convolutional networks and Transformers—and performs reliably on standard image and text classification benchmarks. Experimental results confirm that our estimator closely approximates the accuracy of the weaker model in the pair, often within 1–2% of the ground-truth. Our approach operates entirely on in-distribution unlabeled data, offering a practical and reliable solution for model evaluation in real-world scenarios where labeled validation sets are unavailable.
- 1 September 2025
- Published by Springer Nature in Research Square
Open AccessClassification Accuracy Estimation Without Labels via Architecture-Agnostic Model Agreement
We propose a method to estimate the classification accuracy of a machine learning model without requiring any ground-truth labels, by leveraging the agreement between two models on unlabeled data. Unlike prior work that interprets model agreement as an upper bound or average of model accuracies, we are the first to demonstrate that in heterogeneous, label-free settings, agreement reliably approximates the performance of the weaker model in the pair. Our method is architecture-agnostic and does not require any labeled data, assumptions on model calibration, or prior performance information. We introduce a principled estimator that combines hard-label agreement, probability-level consistency, and a correction term for class imbalance and calibration bias. This estimator remains robust across diverse model types—including convolutional networks and Transformers—and performs reliably on standard image and text classification benchmarks. Experimental results confirm that our estimator closely approximates the accuracy of the weaker model in the pair, often within 1–2% of the ground-truth. Our approach operates entirely on in-distribution unlabeled data, offering a practical and reliable solution for model evaluation in real-world scenarios where labeled validation sets are unavailable.