Tobacco Aerial Dataset: Corrected Image–Mask Pairings and Standardized Test Split

This dataset is derived from the “Tobacco Aerial Dataset” by Imran Moazzam, available at Mendeley Data (DOI: https://doi.org/10.17632/5dpc5gbgpz.2). The dataset was originally introduced in:Moazzam, I.S.; Khan, U.S.; Qureshi, W.S.; Nawaz, T.; Kunwar, F. Towards automated weed detection through two-stage semantic segmentation of tobacco and weed dpixels in aerial imagery. Smart Agricultural Technology 2023, 4, doi:https://doi.org/10.1016/j.atech.2022.100142. This version makes the following modifications: The correction of mismatched image–mask pairings The addition of a test split, with paths to the images in the set. The omission of Campaign no. 2. This version of the dataset was used in:Bunica-Mihai, A., Ichim, L., Popescu, D. (2026). Tobacco and Weed Segmentation from Remote Images Using Artificial Intelligence. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2025. Lecture Notes in Computer Science, vol 16009. Springer, Cham. https://doi.org/10.1007/978-3-032-02728-3_6. The original dataset is licensed under CC BY 4.0, and all original credit belongs to the original authors. Users of this derived dataset should also cite the original dataset and associated publication.