CPN：用于无约束文本检测的互补候选框网络
CPN: Complementary Proposal Network for Unconstrained Text Detection
AI总结：
针对场景文本检测中基于分割和基于锚框方法各自的优缺点，提出互补候选框网络（CPN），通过整合语义与几何候选框及交错特征注意力模块，在相当的计算成本下显著提升了三个基准上的检测性能。
摘要：
现有的场景文本检测方法可分为两种范式：基于分割的和基于锚框的。基于分割的方法虽适合不规则形状，但在紧凑或重叠的布局上表现不佳。相反，，，基于锚框的方法在复杂布局上表现出色，但在不规则形状上表现不佳。为强化其优点并克服各自的缺点，我们提出了一种互补候选框网络（CPN），该网络无缝且并行地整合语义和几何信息以实现卓越性能。CPN包含两个用于候选框生成的高效网络：可变形形态语义网络（Deformable Morphology Semantic Network），它使用创新的可变形形态算子生成语义候选框；以及平衡区域候选框网络（Balanced Region Proposal Network），它利用预定义的锚框生成几何候选框。为进一步增强互补性，我们引入了交错特征注意力（Interleaved Feature Attention）模块，使语义和几何特征在候选框生成前进行深度交互。通过利用互补的候选框和特征，CPN在相当的计算成本下以显著优势超越了最先进的方法。具体而言，我们的方法在具有挑战性的基准 ICDAR19-ArT、IC15 和 MSRA-TD500 上分别实现了 3.6%、1.3% 和 1.0% 的提升。我们方法的代码将被发布。
英文摘要：
Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts. Conversely, anchor-based approaches excel for complex layouts but suffer from irregular shapes. To strengthen their merits and overcome their respective demerits, we propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. The CPN comprises two efficient networks for proposal generation: the Deformable Morphology Semantic Network, which generates semantic proposals employing an innovative deformable morphological operator, and the Balanced Region Proposal Network, which produces geometric proposals with pre-defined anchors. To further enhance the complementarity, we introduce an Interleaved Feature Attention module that enables semantic and geometric features to interact deeply before proposal generation. By leveraging both complementary proposals and features, CPN outperforms state-of-the-art approaches with significant margins under comparable computation cost. Specifically, our approach achieves improvements of 3.6%, 1.3% and 1.0% on challenging benchmarks ICDAR19-ArT, IC15, and MSRA-TD500, respectively. Code for our method will be released.
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。
