arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.07350cs.CV
收藏

The Open Brands Dataset:大规模统一品牌检测和识别

The Open Brands Dataset: Unified brand detection and recognition at scale

Alibaba Group(阿里巴巴集团)

Xuan Jin, Wei Su, Rong Zhang, Yuan He, Hui Xue

摘要:

近年来,随着全球电子商务平台的发展,知识产权保护(IPP)越来越受到关注。品牌认知在IPP中起着重要作用。最近的品牌识别和检测研究是基于小规模的数据集,在探索新兴的深度学习技术时不够全面。而且,在现实和开放的场景中评估品牌检测方法的真实性能是具有挑战性的。为了解决这些问题,我们首先定义的特殊问题,品牌检测和识别相比,一般的目标检测。第二,建立了一个新的品牌基准,称为“开放品牌”。该数据集包含1,437,812张有品牌的图像和50,000张没有任何品牌的图像。Open Brands中包含品牌的部分包含3,113,828个实例,这些实例在3个维度中进行了注释:4种类型,559个品牌和1216个徽标。据我们所知,它是最大的品牌检测和识别数据集,具有丰富的注释。我们提供关于数据集的深入全面的统计数据,验证注释的质量,并研究许多现代模型的性能如何随着训练数据量的增加而演变。第三,我们设计了一个名为“品牌网”的网络来处理品牌识别。与现有的检测方法相比,Brand Net在Open Brand上获得了最先进的mAP。

英文摘要:

Intellectual property protection(IPP) have received more and more attention recently due to the development of the global e-commerce platforms. brand recognition plays a significant role in IPP. Recent studies for brand recognition and detection are based on small-scale datasets that are not comprehensive enough when exploring emerging deep learning techniques. Moreover, it is challenging to evaluate the true performance of brand detection methods in realistic and open scenes. In order to tackle these problems, we first define the special issues of brand detection and recognition compared with generic object detection. Second, a novel brands benchmark called "Open Brands" is established. The dataset contains 1,437,812 images which have brands and 50,000 images without any brand. The part with brands in Open Brands contains 3,113,828 instances annotated in 3 dimensions: 4 types, 559 brands and 1216 logos. To the best of our knowledge, it is the largest dataset for brand detection and recognition with rich annotations. We provide in-depth comprehensive statistics about the dataset, validate the quality of the annotations and study how the performance of many modern models evolves with an increasing amount of training data. Third, we design a network called "Brand Net" to handle brand recognition. Brand Net gets state-of-art mAP on Open Brand compared with existing detection methods.

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。

↑