Unbalanced Datasets Management for the Problem of Segmentation of Satellite Images

Вантажиться...
Ескіз

Дата

2024-10

Науковий керівник

Назва журналу

Номер ISSN

Назва тому

Видавець

IEEE

Анотація

Unbalanced datasets pose significant challenges in the segmentation of satellite images for crop classification tasks. This paper proposes a method to mitigate the bias of models trained on such datasets without the need for additional data collection. The approach involves using spatial weight masks to modify the loss function during model training, assigning higher or lower importance to pixels based on their reliability. The reliability of pixels is determined using algorithms like K-Nearest Neighbors (KNN), and the weight masks undergo various transformations, including morphological operations and Gaussian blur, to refine their texture and ensure smoother transitions between weight factors. Experiments conducted on a dataset of satellite imagery from the Kyiv region demonstrate notable improvements in overall accuracy and Intersection over Union (IoU) when using weight masks that favor normal pixels and apply morphological dilation and Gaussian blur. The proposed method proves particularly beneficial for underrepresented crop types. Additionally, the paper explores the incorporation of synthetic data generated by a Generative Adversarial Network (GAN) alongside real data, revealing slight improvements in recognizing less common crops. Comparative analysis shows that using weight masks offers similar accuracy gains to GAN-based augmentation while being more costeffective by eliminating the need for training an intermediary model and generating additional data. The results suggest that the proposed method of using spatial weight masks is a viable and efficient approach to managing unbalanced datasets in satellite image segmentation for crop classification tasks.

Опис

Ключові слова

KNN, Dataset Quality Assessment, Imbalanced Datasets, Hard Cases, Crop Classification, Generative Adversarial Networks, Training Data Generation, Data Set Imbalance, U- Net

Бібліографічний опис

Okhrimenko, A. Unbalanced Datasets Management for the Problem of Segmentation of Satellite Images / Anton Okhrimenko, Nataliia Kussul // 2024 IEEE Fourth International Conference on System Analysis & Intelligent Computing (SAIC), [Kyiv], 8-10 October 2024. - Kyiv, 2024. - 6 p.

DOI