RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning
This addresses the problem of developing broadly applicable models for ARS vision, which is incremental as it builds on existing foundation model research but adapts it to a specific domain.
The paper tackled the challenge of limited applicability in Aerial Remote Sensing (ARS) vision tasks by proposing RingMo-Aerial, a foundation model that achieved state-of-the-art performance on multiple downstream tasks.
Aerial Remote Sensing (ARS) vision tasks present significant challenges due to the unique viewing angle characteristics. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad range of ARS vision applications. This paper proposes RingMo-Aerial, aiming to fill the gap in foundation model research in the field of ARS vision. A Frequency-Enhanced Multi-Head Self-Attention (FE-MSA) mechanism is introduced to strengthen the model's capacity for small-object representation. Complementarily, an affine transformation-based contrastive learning method improves its adaptability to the tilted viewing angles inherent in ARS tasks. Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and performance in various ARS vision tasks. Experimental results demonstrate that RingMo-Aerial achieves SOTA performance on multiple downstream tasks. This indicates the practicality and efficacy of RingMo-Aerial in enhancing the performance of ARS vision tasks.