Multiple Distribution Shift -- Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation
This work addresses the challenge of out-of-distribution performance for researchers in computer vision and aerial imagery, but it is incremental as it primarily provides a new dataset and baseline evaluations.
The authors tackled the problem of machine learning model performance degradation under distribution shifts by introducing the MDS-A dataset, a collection of simulated aerial datasets with different weather conditions, and reported performance results for baseline object-detection models and error-detection techniques on this data.
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.