Kronecker Product Feature Fusion for Convolutional Neural Network in Remote Sensing Scene Classification
This work addresses a domain-specific problem in remote sensing scene classification, offering an incremental improvement in feature fusion techniques.
The paper tackles remote sensing scene classification by proposing a novel feature fusion algorithm using the Kronecker product to unify existing methods like Add and Concat, resulting in enhanced CNN accuracy as demonstrated in experiments.
Remote Sensing Scene Classification is a challenging and valuable research topic, in which Convolutional Neural Network (CNN) has played a crucial role. CNN can extract hierarchical convolutional features from remote sensing imagery, and Feature Fusion of different layers can enhance CNN's performance. Two successful Feature Fusion methods, Add and Concat, are employed in certain state-of-the-art CNN algorithms. In this paper, we propose a novel Feature Fusion algorithm, which unifies the aforementioned methods using the Kronecker Product (KPFF), and we discuss the Backpropagation procedure associated with this algorithm. To validate the efficacy of the proposed method, a series of experiments are designed and conducted. The results demonstrate its effectiveness of enhancing CNN's accuracy in Remote sensing scene classification.