无提示通用区域提议网络
Prompt-Free Universal Region Proposal Network
提出一种无需图像/文本提示的通用区域提议网络，用可学习查询嵌入配合稀疏图像感知适配器与级联自提示完成潜在目标定位，可直接迁移到水下、工业缺陷、遥感等域外检测场景而无需微调，为开放场景下的类无关提议生成提供了可复用范式。
原文依据 we introduce a novel Prompt-Free Universal Region Proposal Network (PF-RPN), which identifies potential objects without relying on external prompts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论识别潜在目标对于各类计算机视觉应用中的目标识别与分析至关重要。现有方法通常依赖示例图像、预定义类别或文本描述来定位潜在目标。然而，对图像与文本提示的依赖往往限制了灵活性，削弱了在真实场景中的适应性。本文提出一种新颖的无提示通用区域提议网络（PF-RPN），无需依赖外部提示即可识别潜在目标。首先，稀疏图像感知适配器（SIA）模块利用随视觉特征动态更新的可学习查询嵌入，对潜在目标进行初步定位。接着，级联自提示（CSP）模块借助自提示的可学习嵌入识别其余潜在目标，以级联方式自主聚合信息丰富的视觉特征。最后，中心度引导查询选择（CG-QS）模块通过中心度评分网络促进高质量查询嵌入的选取。本方法可在有限数据（例如 MS COCO 数据的 5%）上优化，并可直接应用于各类目标检测应用领域以识别潜在目标而无需微调，如水下目标检测、工业缺陷检测和遥感图像目标检测。在 19 个数据集上的实验结果验证了本方法的有效性。
英文原文摘要 1482 字符
Identifying potential objects is critical for object recognition and analysis across various computer vision applications. Existing methods typically localize potential objects by relying on exemplar images, predefined categories, or textual descriptions. However, their reliance on image and text prompts often limits flexibility, restricting adaptability in real-world scenarios. In this paper, we introduce a novel Prompt-Free Universal Region Proposal Network (PF-RPN), which identifies potential objects without relying on external prompts. First, the Sparse Image-Aware Adapter (SIA) module performs initial localization of potential objects using a learnable query embedding dynamically updated with visual features. Next, the Cascade Self-Prompt (CSP) module identifies the remaining potential objects by leveraging the self-prompted learnable embedding, autonomously aggregating informative visual features in a cascading manner. Finally, the Centerness-Guided Query Selection (CG-QS) module facilitates the selection of high-quality query embeddings using a centerness scoring network.Our method can be optimized with limited data (e.g., 5% of MS COCO data) and applied directly to various object detection application domains for identifying potential objects without fine-tuning, such as underwater object detection, industrial defect detection, and remote sensing image object detection. Experimental results across 19 datasets validate the effectiveness of our method.