Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.13289 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913698171322368 |
|---|---|
| author | Ngu, Noel Taparia, Aditya Simari, Gerardo I. Leiva, Mario Corcoran, Jack Senanayake, Ransalu Shakarian, Paulo Bastian, Nathaniel D. |
| author_facet | Ngu, Noel Taparia, Aditya Simari, Gerardo I. Leiva, Mario Corcoran, Jack Senanayake, Ransalu Shakarian, Paulo Bastian, Nathaniel D. |
| contents | Machine learning models assume that training and test samples are drawn from the same distribution. As such, significant differences between training and test distributions often lead to degradations in performance. We introduce Multiple Distribution Shift -- Aerial (MDS-A) -- a collection of inter-related datasets of the same aerial domain that are perturbed in different ways to better characterize the effects of out-of-distribution performance. Specifically, MDS-A is a set of simulated aerial datasets collected under different weather conditions. We include six datasets under different simulated weather conditions along with six baseline object-detection models, as well as several test datasets that are a mix of weather conditions that we show have significant differences from the training data. In this paper, we present characterizations of MDS-A, provide performance results for the baseline machine learning models (on both their specific training datasets and the test data), as well as results of the baselines after employing recent knowledge-engineering error-detection techniques (EDR) thought to improve out-of-distribution performance. The dataset is available at https://lab-v2.github.io/mdsa-dataset-website. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multiple Distribution Shift -- Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation Ngu, Noel Taparia, Aditya Simari, Gerardo I. Leiva, Mario Corcoran, Jack Senanayake, Ransalu Shakarian, Paulo Bastian, Nathaniel D. Machine Learning Machine learning models assume that training and test samples are drawn from the same distribution. As such, significant differences between training and test distributions often lead to degradations in performance. We introduce Multiple Distribution Shift -- Aerial (MDS-A) -- a collection of inter-related datasets of the same aerial domain that are perturbed in different ways to better characterize the effects of out-of-distribution performance. Specifically, MDS-A is a set of simulated aerial datasets collected under different weather conditions. We include six datasets under different simulated weather conditions along with six baseline object-detection models, as well as several test datasets that are a mix of weather conditions that we show have significant differences from the training data. In this paper, we present characterizations of MDS-A, provide performance results for the baseline machine learning models (on both their specific training datasets and the test data), as well as results of the baselines after employing recent knowledge-engineering error-detection techniques (EDR) thought to improve out-of-distribution performance. The dataset is available at https://lab-v2.github.io/mdsa-dataset-website. |
| title | Multiple Distribution Shift -- Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.13289 |