发表机构
Wuhan Textile University; Wuhan University; Ohio State University（武汉纺织大学; 武汉大学; 俄亥俄州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对遥感图像开放世界目标检测中欧氏空间难以表征类别层次关系的问题，提出基于双曲几何的HyRS-OWOD方法，通过解耦目标性学习、双曲不确定性学习和双曲度量学习提升未知目标召回与增量学习性能，并在三个基准上验证了有效性。
AI 中文摘要
开放世界目标检测（OWOD）通过要求模型识别未知目标并在注释可用时增量学习它们，扩展了封闭集检测。在遥感图像中，目标类别通常表现出潜在的层次关系，这些关系在现有方法普遍采用的欧几里得空间中可能无法得到充分表示，从而限制了未知目标召回率和增量学习性能。为解决此问题，我们研究了用于遥感图像中OWOD的双曲几何，并提出了HyRS-OWOD。为提高未知目标召回率，我们设计了一个两步未知目标发现机制：一个解耦目标性学习（DOL）模块，将前景感知与语义信息分离，以将前景提议与背景区域区分开；随后是一个双曲不确定性学习（HUL）组件，利用双曲嵌入的半径作为不确定性感知线索，用于已知与未知的判别。对于增量学习，我们开发了一种双曲度量学习（HML）策略，增强类间可分性，促进新类别的纳入，同时减轻灾难性遗忘。在三个遥感基准上的实验表明，与最先进的OWOD方法相比，在未知召回率和增量学习方面均取得了一致的改进。
英文摘要
Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annotations become available. In remote sensing imagery, object categories often exhibit latent hierarchical relationships that may be inadequately represented in the Euclidean spaces commonly adopted by existing methods, limiting unknown-object recall and incremental-learning performance. To address this issue, we investigate hyperbolic geometry for OWOD in remote sensing imagery and propose HyRS-OWOD. To improve unknown object recall, we design a two-step unknown-object discovery mechanism: a Decoupled Objectness Learning (DOL) module that disentangles foreground perception from semantic information to separate foreground proposals from background regions, followed by a Hyperbolic Uncertainty Learning (HUL) component that leverages the radius of hyperbolic embeddings as an uncertainty-aware cue for known-unknown discrimination. For incremental learning, we develop a Hyperbolic Metric Learning (HML) strategy that enhances inter-class separability, facilitating the incorporation of novel categories while mitigating catastrophic forgetting. Experiments on three remote sensing benchmarks demonstrate consistent improvements in unknown recall and incremental learning over state-of-the-art OWOD methods.
