A Bi-Prototype BDC Metric Network With Lightweight Adaptive Task Attention for Few-Shot Fine-Grained Ship Classification in Remote Sensing Images

Fine-grained ship classification in optical remote sensing images is a major challenge in the ocean observation field, elaborated as follows: first, the cost of acquiring ship images is expensive. Obtaining numerous labeled samples is difficult, resulting in the poor generalization ability of training models. Second, the features of ship target cannot be accurately obtained owing to complex background interference. Third, interclass similarity and intraclass diversity among different ships render ship classification difficult. In this study, we propose lightweight adaptive task attention-bi-prototype-Brownian distance covariance (LATA-BP-BDC): a BP-BDC metric network with LATA for few-shot fine-grained ship classification. First, the LATA module is used to generate 3-D weights, which can effectively reduce complex background interference and improve the adaptive capturing ability of target features without including additional network operators. Second, we input target features into the BDC metric module and output the BDC matrices to represent image information. Because the similarity between two images can be calculated as the corresponding BDC matrices distance, the improvement of the relevance of similar targets can be realized. Finally, we use the bi-prototype module to generate highly accurate prototypes, further calibrating information differences between images, which enhances the correlation between the same category samples and separability between different categories samples. Consequently, this process effectively reduces the influence of large intraclass appearance variation and small interclass appearance variation. We perform validation using two fine-grained datasets, fine-grained ship classification in remote sensing images (FGSCR), and caltech-ucsd birds-200-2011 (CUB). Compared with the state-of-the-art methods, the LATA-BP-BDC achieves a superior performance and has good generalization for fine-grained few-shot classification.

Automated summary

Fine-grained ship classification in optical remote sensing images is a challenging task in the ocean observation field due to the expensive cost of acquiring ship images, complex background interference, and the similarity and diversity among different ships. In this study, a lightweight adaptive task attention-bi-prototype-Brownian distance covariance (LATA-BP-BDC) method is proposed to address these challenges and achieve superior performance in few-shot ship classification.