Architectures based on siamese networks with triplet loss have shown outstanding performance on the image-based similarity search problem. This approach attempts to discriminate between positive (relevant) and negative (irrelevant) items. However, it undergoes a critical weakness. Given a query, it cannot discriminate weakly relevant items, for instance, items of the same type but different color or texture as the given query, which could be a serious limitation for many real-world search applications. Therefore, in this work, we present a quadruplet-based architecture that overcomes the aforementioned weakness. Moreover, we present an instance of this quadruplet network, which we call Sketch-QNet, to deal with the color sketch-based image retrieval (CSBIR) problem, achieving new state-of-the-art results.

翻译：基于三重损失的硅网络结构显示图像相近搜索问题的出色表现。 这种方法试图区分正( 相关) 和负( 无关) 项。 但是, 它存在一个严重的弱点 。 由于询问, 它不能对相关项目进行微弱的区分, 例如, 与给定查询相同类型, 但颜色或质地不同的项目, 这可能会严重限制许多真实世界搜索应用程序。 因此, 在这项工作中, 我们提出了一个基于四重的架构, 克服了上述弱点 。 此外, 我们举了一个四重网络的例子, 我们称之为 Scetch- QNet, 来处理基于彩色素描图的图像检索问题, 从而实现新的最新结果 。