Image copy detection is of great importance in real-life social media. In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21. In D$^2$LV, unsupervised pre-training substitutes the commonly-used supervised one. When training, we design a set of basic and six advanced transformations, and a simple but effective baseline learns robust representation. During testing, a global-local and local-global matching strategy is proposed. The strategy performs local-verification between reference and query images. Experiments demonstrate that the proposed method is effective. The proposed approach ranks first out of 1,103 participants on the Facebook AI Image Similarity Challenge: Matching Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track1-Submission.
翻译：在现实生活中的社交媒体中,图像复制检测非常重要。 在本文中,提出了一种数据驱动和地方验证(D$2$LV)方法,以竞争图像相似性挑战:匹配NeurIPS'21的轨迹。在D$2$LV中,未受监督的培训前替代品是常用的监督下的。在培训时,我们设计一套基本和六种先进转换,以及简单而有效的基准,学习强健的代表性。在测试期间,提出了一种全球和地方-全球匹配战略。该战略在参考和查询图像之间进行地方验证。实验表明拟议的方法是有效的。拟议方法在Facebook AI 图像相似性挑战:匹配轨道上的1 103名参与者中排第一。该代码和经过培训的模型可在https://github.com/WangWenhao0716/ISC-Trac11-Submission上查阅。
相关内容
微信扫码咨询专知VIP会员