MSRIP-Net: Addressing Interpretability and Accuracy Challenges in Aircraft Fine-Grained Recognition of Remote Sensing Images

The task of fine-grained aircraft recognition is crucial in the field of remote sensing. Despite some progress achieved by traditional deep learning methods in addressing this challenge, they are often perceived as a “black box,” lacking transparent explanations for model decisions. Current interpretable methods based on attention mechanisms, although providing some interpretability, do not align with human thought logic. Therefore, we propose a multiscale rotation-invariant prototype network (MSRIP-Net). Our approach simulates the intuitive reasoning process of humans in identifying objects by segmenting them into multiple components. Importantly, MSRIP-Net has the capability to automatically recognize rigid components on aircraft targets without relying on additional part annotations, using only image-level class labels. In addition, our approach effectively addresses challenges presented by noise, deformations, and multiscale variations in remote sensing targets and has been comprehensively evaluated on datasets FAIR1M1.0 and Rareplane. Our results demonstrate that MSRIP-Net achieves higher accuracy compared with existing fine-grained recognition methods. Furthermore, we provide insights into the model’s decision-making process to illustrate the interpretability of our approach.

I. Introduction

With the development of remote sensing technology, the aircraft fine-grained recognition is a crucial task in the interpretation of remote sensing images, which plays a vital role in military and civilian fields, such as mission planning, security, surveillance, and military decision making [1], [2], [3], [4], [5]. Therefore, in practical application scenarios, achieving high-precision classification results alone is no longer sufficient, what is imperative is the utilization of highly interpretable methods.