Focal-Hinge Loss based Deep Hybrid Framework for imbalanced Remote Sensing Scene Classification

Abstract

Deep learning models have received a significant breakthrough in remote sensing scene clas-
sification due to their discriminative, hierarchical feature extraction ability. Nevertheless, CNN-based
methods deliver accurate classification results only with sufficient annotated training samples. The com-
putational bottleneck of CNNs with numerous parameters in case of inadequate training samples and the
inherent class imbalance problem in high-resolution satellite Scene Classification question the perfor-
mance of the Classifier. Existing Deep CNNs with conventional Cross-Entropy loss function neglected
the significance of gradient contribution from minority classes in handling imbalanced LULC class dis-
tribution. In this context, we propose the hybrid probabilistic gradient-based deep learning framework
CNN-FHSVM with regularized novel Focal-Hinge loss cost function optimization for alleviating mis-
classifications in imbalanced datasets. The empirical experimentation with Sentinel 2 EuroSat Dataset
benchmarked for deep learning algorithms demonstrated that the proposed model is superior in miti-
gating classification errors in imbalanced class distribution contrasted to the cutting-edge deep learning
frameworks. The proposed loss function adaptively updates the gradient of the minority classes, drifting
the focus to misclassified scenes. Focal-Hinge loss is the first endeavor adapted to remote sensing LULC
multiclass classification for reducing misclassifications. The model demonstrates higher accuracy with
reduced misclassifications and training time and can benefit other remote sensing applications like early
deforestation , urban planning, where LULC maps are imbalanced.