Importance of Disjoint Sampling in Conventional and Transformer Models for Hyperspectral Image Classification
This addresses the need for rigorous and unbiased benchmarking in hyperspectral image classification, which is critical for advancing state-of-the-art models and their real-world applications in large-scale land mapping.
The paper tackles the problem of biased evaluation in hyperspectral image classification by proposing a disjoint sampling approach that separates training, validation, and test data without overlap, resulting in significantly improved model generalization compared to methods with data leakage.
Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models. When training, validation, and test sets overlap or share data, it introduces a bias that inflates performance metrics and prevents accurate assessment of a model's true ability to generalize to new examples. This paper presents an innovative disjoint sampling approach for training SOTA models on Hyperspectral image classification (HSIC) tasks. By separating training, validation, and test data without overlap, the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation. Experiments demonstrate the approach significantly improves a model's generalization compared to alternatives that include training and validation data in test data. By eliminating data leakage between sets, disjoint sampling provides reliable metrics for benchmarking progress in HSIC. Researchers can have confidence that reported performance truly reflects a model's capabilities for classifying new scenes, not just memorized pixels. This rigorous methodology is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors. The source code is available at https://github.com/mahmad00/Disjoint-Sampling-for-Hyperspectral-Image-Classification.