A Prototype Network for Hyperspectral Image Open-Set Classification Based on Feature Invariance and Weighted Pearson Distance Measurement
Yuefan Du, Xiaoping Li, Lei Shi, Fangyan Li, Tuo Xu
Abstract
This study investigates the use of Hyperspectral Images (HSI) in remote sensing technology, focusing on the challenges of open-set classification. The high-dimensionality and complexity of HSI bring unparalleled depth and precision to remote sensing, yet pose significant classification challenges. To address these challenges, we introduce a novel prototype network based on feature invariance for open-set HSI classification (FIWPPN). This network utilizes a ResNet architecture to extract spectral-spatial features and includes an invariance clustering module to enhance feature boundary delineation in the prototype network classification. Furthermore, we have developed a weighted Pearson distance metric to establish a measurement domain between unlabeled data and training data, facilitating open-set recognition. Experimental validation on three publicly accessible HSI datasets demonstrates that our method surpasses existing classification techniques in terms of classification accuracy and open-set classification performance.