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.

翻译：标志检测在众多应用中发挥着不可或缺的作用。然而，处理小标志仍然具有挑战性，因为它们在图像中占据的像素过少，增加了提取判别性特征的难度。小标志的聚集也给标志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面向小标志检测的跨方向任务解耦网络（CTDNet）。首先引入跨方向特征金字塔（CFP），通过水平传输和垂直传输实现跨方向特征融合。此外，多频率任务解耦头（MTDH）将分类和定位任务解耦为两个分支。设计了一种多频率注意力卷积分支，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。在四个标志数据集上的综合实验验证了所提方法的有效性和高效性。