无提示通用区域提议网络
Prompt-Free Universal Region Proposal Network
AI总结：
本文提出无提示通用区域提议网络PF-RPN，通过自适应查询嵌入和级联自提示模块实现无需外部提示的对象定位，适用于多种目标检测场景。
摘要：
识别潜在对象对于各种计算机视觉应用中的目标识别和分析至关重要。现有方法通常依赖于示例图像、预定义类别或文本描述来定位潜在对象。然而，其对图像和文本提示的依赖限制了灵活性，限制了在现实世界中的适应性。本文介绍了一种新的无提示通用区域提议网络（PF-RPN），该网络无需依赖外部提示即可识别潜在对象。首先，稀疏图像感知适配器（SIA）模块通过可学习的查询嵌入进行初始定位，该嵌入动态更新与视觉特征相关。接下来，级联自提示（CSP）模块利用自提示的可学习嵌入，自主地以级联方式聚合信息性视觉特征。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择。我们的方法可以使用有限的数据（例如MS COCO数据的5%）进行优化，并可直接应用于各种目标检测应用领域，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该方法的有效性。代码可在https://github.com/tangqh03/PF-RPN上获得。
英文摘要：
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. Code is available at https://github.com/tangqh03/PF-RPN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
