paper-with-me

홈 › Papers

A Cross-direction Task Decoupling Network for Small Logo Detection

2023-05-04 · Hou, Sujuan, Xingzhuo, Min, Weiqing, Li, Jiacheng, Wang, Jing, Zheng, Yuanjie, Jiang, Shuqiang

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.

📄 PDF Abstract BibTeX arXiv:2305.02503

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network

2021-08-10 · Qiang Hou, Weiqing Min, Jing Wang, Sujuan Hou 외

Food logo detection plays an important role in the multimedia for its wide real-world applications, such as food recommendation of the self-service shop and infringement detection on e-commerce platforms. A large-scale f…

Food recommendation

Deep Learning for Logo Detection: A Survey

2022-10-10 · Sujuan Hou, Jiacheng Li, Weiqing Min, Qiang Hou 외

When logos are increasingly created, logo detection has gradually become a research hotspot across many domains and tasks. Recent advances in this area are dominated by deep learning-based solutions, where many datasets,…

Deep LearningSurvey

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector

2025-10-14 · Sifan Li, Hongkai Chen, Yujun Cai, Qingwen Ye 외 arxiv

Vision Language Models (VLMs) have achieved impressive progress in multimodal reasoning; yet, they remain vulnerable to hallucinations, where outputs are not grounded in visual evidence. In this paper, we investigate a p…

Multimodal Reasoning

Open Set Logo Detection and Retrieval

2017-10-30 · Andras Tüzkö, Christian Herrmann, Daniel Manger, Jürgen Beyerer

Current logo retrieval research focuses on closed set scenarios. We argue that the logo domain is too large for this strategy and requires an open set approach. To foster research in this direction, a large-scale logo da…

Retrieval

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

2021-08-31 · Baisong Zhang, Weiqing Min, Jing Wang, Sujuan Hou 외

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 ge…

Managementobject-detectionObject Detection