Lightweight Fine-Grained Recognition Method Based on Multilevel Feature Weighted Fusion

Abstract

Fine-grained recognition in remote sensing images has played a critical role in military and civil fields. Recently, with the rapid growth of convolutional neural networks (CNNs), many fine-grained recognition methods have been proposed. However, due to the large amount of parameters and computational complexity, it is difficult to apply these methods in practical applications. To this end, we propose a novel lightweight fine-grained recognition method based on multilevel feature weighted fusion. First, we design a lightweight CNN (LCNN) framework. Second, we propose a multilevel feature weighted fusion method to improve the recognition accuracy. Third, we adopt a feature channel based loss function to train the proposed model end-to-end. Experiments are conducted on the challenging remote sensing dataset MTARSI to evaluate our proposed method. The results show that the proposed method can achieve state-of-the-art performance.