论文标题
实用图像副本检测的基准和不对称相似性学习
A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
论文作者
论文摘要
图像复制检测（ICD）旨在确定查询图像是否是参考集中的任何图像的编辑副本。目前，ICD的公共基准非常有限，而在现实世界中，遍布整个挑战，即对硬性负面查询的注意力。具体而言，某些查询不是编辑的副本，而是与某些参考图像的本质相似。这些硬负查询很容易被错误地识别为已编辑的副本，从而严重损害了ICD的精度。这种观察促使我们构建了以这种特征为特征的第一个ICD基准。基于现有的ICD数据集，本文通过分别在培训和测试集中添加100、000和24、252硬负对来构建新数据集。此外，本文进一步揭示了解决ICD中严重负面问题的独特困难，即当前的度量学习与ICD之间存在根本的冲突。这场冲突是：公制学习采用对称距离，而编辑的副本是不对称的（单向）过程，例如，部分作物接近其整体参考图像，并且是编辑的副本，而后者则不能是前者的编辑副本（以较小的距离相同）。这种洞察力导致不对称的相似性学习（ASL）方法，该方法允许在两个方向上的相似性（查询<->参考图像）彼此不同。实验结果表明，ASL通过明确的边缘胜过最先进的方法，证实解决对称 - 对称冲突对于ICD至关重要。 NDEC数据集和代码可在https://github.com/wangwenhao0716/asl上找到。
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.
