Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

Abstract

Recently, logo detection has received more and more attention for its wide applications in the multimedia field, such as intellectual property protection, product brand management, and logo duration monitoring. Unlike general object detection, logo detection is a challenging task, especially for small logo objects and large aspect ratio logo objects in the real-world scenario. In this paper, we propose a novel approach, named Discriminative Semantic Feature Pyramid Network with Guided Anchoring (DSFP-GA), which can address these challenges via aggregating the semantic information and generating different aspect ratio anchor boxes. More specifically, our approach mainly consists of Discriminative Semantic Feature Pyramid (DSFP) and Guided Anchoring (GA). Considering that lowlevel feature maps that are used to detect small logo objects lack semantic information, we propose the DSFP, which can enrich more discriminative semantic features of low-level feature maps and can achieve better performance on small logo objects. Furthermore, preset anchor boxes are less efficient for detecting large aspect ratio logo objects. We therefore integrate the GA into our method to generate large aspect ratio anchor boxes to mitigate this issue. Extensive experimental results on four benchmarks demonstrate the effectiveness of our proposed DSFP-GA. Moreover, we further conduct visual analysis and ablation studies to illustrate the advantage of our method in detecting small and large aspect logo objects. The code and models can be found at https://github.com/Zhangbaisong/DSFP-GA.

Few‐shot logo detection

“…Considering this characteristic, Hou et al [1] proposed Multiscale Feature Decoupling Network (MFDNet), which decouples the classification and regression heads into two branches, and then focuses attention on the classification head. Considering both the small and large aspect ratios in logo images, Zhang et al [3] proposed Discriminative Semantic Feature Pyramid Network with Guided Anchoring (DSFP-GA), they aggregate semantic information and generate anchor boxes with different aspect ratios. Wang et al [2] created a large scale dataset called LogoDet-3K, and they incorporated the Focal loss and CIoU loss into YOLOv3.…”

“…The obtained R I is then re-scaled using the same but opposite way of integration to reinforce the features. 3…”

“…A logo can be used to distinguish a brand from the markets and select appropriate products during online shopping. Due to the importance and particularity of logo in corporate culture, and the rate at which logo infringement occurs nowadays, it is crucial to develop logo detection techniques [1][2][3] to ensure the sanctity of genuine logos. Besides, logo detection also has significant importance in a number of practical applications, such as commodity recommendation, commercial publicity, intelligent transportation, auto-driving and illegal logo detection amongst others.…”