用于小Logo检测的跨方向任务解耦网络
A Cross-direction Task Decoupling Network for Small Logo Detection
AI总结：
针对小Logo检测中特征提取难、聚集Logo分类定位难的问题，提出CTDNet，通过CFP跨方向融合特征、MTDH解耦任务并结合离散余弦变换设计多频注意力卷积分支，在四个数据集上验证了有效性与高效性。
摘要：
Logo检测在诸多应用中发挥着不可或缺的作用。然而，处理小型Logo仍然颇具难度，因为它们在图像中占据的像素过少，这给判别性特征的提取带来了负担。小型Logo的聚集也为Logo的分类与定位带来了巨大挑战。为解决这些问题，我们创新性地提出了用于小Logo检测的跨方向任务解耦网络（Cross-direction Task Decoupling Network, CTDNet）。我们首先引入跨方向特征金字塔（Cross-direction Feature Pyramid, CFP），通过采用水平传输与垂直传输实现跨方向特征融合。此外，多频任务解耦头（Multi-frequency Task Decoupling Head, MTDH）将分类与定位任务解耦为两个分支。我们设计了一个多频注意力卷积分支，通过创新性地结合离散余弦变换与卷积实现更精准的回归。在四个Logo数据集上开展的综合实验证明了所提方法的有效性与高效性。
英文摘要：
Logo detection plays an integral role in many applications. However, handling small logos is still difficult since they occupy too few pixels in the image, which burdens the extraction of discriminative features. The aggregation of small logos also brings a great challenge to the classification and localization of logos. To solve these problems, we creatively propose Cross-direction Task Decoupling Network (CTDNet) for small logo detection. We first introduce Cross-direction Feature Pyramid (CFP) to realize cross-direction feature fusion by adopting horizontal transmission and vertical transmission. In addition, Multi-frequency Task Decoupling Head (MTDH) decouples the classification and localization tasks into two branches. A multi frequency attention convolution branch is designed to achieve more accurate regression by combining discrete cosine transform and convolution creatively. Comprehensive experiments on four logo datasets demonstrate the effectiveness and efficiency of the proposed method.
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。
