提出面向航拍遥感的通用模型，提升小目标识别与倾斜视角适应性。
RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning
- 引入频增强自注意力机制，强化小物体表征能力。
- 基于仿射变换的对比学习，提升对倾斜视角的适应性。
- 提出高效微调模块，适配多种航拍任务，性能领先。
航拍遥感（ARS）视觉任务因独特的俯视视角特性面临严峻挑战。现有研究多聚焦特定任务算法，难以泛化至广泛应用场景。本文提出RingMo-Aerial，填补航拍遥感领域基础模型研究空白。引入频增强多头自注意力（FE-MSA）机制，增强模型对小目标的表征能力；提出基于仿射变换的对比学习方法，提升模型对航拍中固有倾斜视角的适应性；并设计高效的ARS-Adapter参数微调方法，提升模型在各类航拍视觉任务中的适配性与性能。实验表明，RingMo-Aerial在多个下游任务上达到最先进水平，验证了其在提升航拍遥感任务性能方面的实用性与有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。