Multiple Distribution Shift-Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation

Noel Ngu, Aditya Taparia, Gerardo I. Simari, Mario A. Leiva, Ransalu Senanayake, Paulo Shakarian, Nathaniel D. Bastian, John Corcoran

Proceedings of the AAAI Symposium Series, 2025

picture_as_pdf PDF
Sample imagery from the MDS-A dataset, showing aerial scenes rendered under multiple simulated distribution shifts.

Summary

We present MDS-A, a dataset of simulated aerial imagery paired with explicitly controlled distribution shifts, built for evaluating test-time error detection and model adaptation methods under conditions where a single held-out test set would not expose failure.

BibTeX

@inproceedings{ngu2025multiple,
    title={Multiple Distribution Shift-Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation},
    author={Ngu, Noel and Taparia, Aditya and Simari, Gerardo I. and Leiva, Mario A. and Senanayake, Ransalu and Shakarian, Paulo and Bastian, Nathaniel D. and Corcoran, John},
    booktitle={Proceedings of the AAAI Symposium Series},
    volume={5},
    pages={379--383},
    year={2025}
}