Makeup216: Logo Recognition with Adversarial Attention Representations

• DOI: 10.48550/arxiv.2112.06533
• Publication Date: 2021-01-01
• Authors: Junjun Hu; Yanhao Zhu; Bo Zhao; Jiexin Zheng; Chenxu Zhao; Xiangyu Zhu; Kangle Wu; Darun Tang
• Keywords: Logo (programming language); Logos Bible Software; Representation; Discriminative model

One of the challenges logo recognition lies in diversity forms, such as symbols, texts or a combination both; further, logos tend to be extremely concise design while similar appearance, suggesting difficulty learning discriminative representations. To investigate variety and representation logo, we introduced Makeup216, largest most complex dataset field makeup, captured from real world. It comprises 216 157 brands, including 10,019 images 37,018 annotated objects. In addition, found that marginal background around pure can provide important context information proposed an adversarial attention framework (AAR) attend on subject auxiliary separately, which combined for better representation. Our achieved competitive results Makeup216 another large-scale open dataset, could fresh thinking recognition. The code will released soon.