Image copy detection (ICD) aims to determine whether a query image is an edited copy of any image from a reference set. Currently, there are very limited public benchmarks for ICD, while all overlook a critical challenge in real-world applications, i.e., the distraction from hard negative queries. Specifically, some queries are not edited copies but are inherently similar to some reference images. These hard negative queries are easily false recognized as edited copies, significantly compromising the ICD accuracy. This observation motivates us to build the first ICD benchmark featuring this characteristic. Based on existing ICD datasets, this paper constructs a new dataset by additionally adding 100, 000 and 24, 252 hard negative pairs into the training and test set, respectively. Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i.e., there is a fundamental conflict between current metric learning and ICD. This conflict is: the metric learning adopts symmetric distance while the edited copy is an asymmetric (unidirectional) process, e.g., a partial crop is close to its holistic reference image and is an edited copy, while the latter cannot be the edited copy of the former (in spite the distance is equally small). This insight results in an Asymmetrical-Similarity Learning (ASL) method, which allows the similarity in two directions (the query <-> the reference image) to be different from each other. Experimental results show that ASL outperforms state-of-the-art methods by a clear margin, confirming that solving the symmetric-asymmetric conflict is critical for ICD. The NDEC dataset and code are available at https://github.com/WangWenhao0716/ASL.
翻译:图像复制检测 ( ICD) 旨在确定查询图像是否是来自参考集的任何图像的编辑副本 。 目前, ICD 的公开基准非常有限, 而所有都忽略了真实世界应用程序中的一个关键挑战, 即对硬否定查询的分心。 具体地说, 有些查询不是编辑副本, 但本质上与某些参考图像相似。 这些硬否定查询很容易被误认为编辑副本, 大大降低 ICD 的准确性 。 此观察激励我们建立第一个以该特性为特征的 ICD 基准 。 根据现有的 ICD 数据集, 本文构建了一个新的数据集, 在培训和测试集中分别添加了 100, 000 和 24, 252 对硬负对子。 此外, 本文还进一步揭示了解决 ICD 硬否定问题的独特困难, 也就是说, 目前的基准学习与 ICD 之间的基本冲突是被识别为编辑副本, 而经编辑的版本( usionalionalionalionalal) 进程, 例如, 部分作物接近其整体参考图像图像, 并且是一个类似的版本, AS a descrialalalalal 。 数据不能被复制, 而后又被复制为另一种版本。 a exal exal exal exal 。