首个支持遥感图像开放词汇计数的模型，能识别训练时未见的新物体。
RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data
- 基于文本或视觉提示实现对未见物体的计数
- 在未标注新类别的场景下仍保持高精度计数
- 适合动态监测中需快速适应新目标的应用
遥感图像中的目标计数因其在众多应用中的关键作用而受到越来越多关注。尽管已有多种有前景的遥感计数方法被提出，但现有方法仅针对预定义的封闭类别集。这一局限性要求对新物体进行昂贵的重新标注和模型重训练，严重限制了其在动态真实监测场景中的应用。为此，本文提出首个面向遥感与航空影像的开放词汇计数（RS-OVC）模型。实验表明，该模型仅依赖文本或视觉条件，即可对训练中未见过的新物体类别实现准确计数。
原文摘要 · Abstract (English)
Object-Counting for remote-sensing (RS) imagery is attracting increasing research interest due to its crucial role in a wide and diverse set of applications. While several promising methods for RS object-counting have been proposed, existing methods focus on a closed, pre-defined set of object classes. This limitation necessitates costly re-annotation and model re-training to adapt current approaches for counting of novel objects that have not been seen during training, and severely inhibits their application in dynamic, real-world monitoring scenarios. To address this gap, in this work we propose RS-OVC - the first Open Vocabulary Counting (OVC) model for Remote-Sensing and aerial imagery. We show that our model is capable of accurate counting of novel object classes, that were unseen during training, based solely on textual and/or visual conditioning.
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。