Hard negative generation aims to generate informative negative samples that help to determine the decision boundaries and thus facilitate advancing deep metric learning. Current works select pair/triplet samples, learn their correlations, and fuse them to generate hard negatives. However, these works merely consider the local correlations of selected samples, ignoring global sample correlations that would provide more significant information to generate more informative negatives. In this work, we propose a globally correlation-aware hard negative generation (GCA-HNG) framework, which first learns sample correlations from a global perspective and exploits these correlations to guide generating hardness-adaptive and diverse negatives. Specifically, this approach begins by constructing a structured graph to model sample correlations, where each node represents a specific sample and each edge represents the correlations between corresponding samples. Then, we introduce an iterative graph message propagation to propagate the messages of node and edge through the whole graph and thus learn the sample correlations globally. Finally, with the guidance of the learned global correlations, we propose a channel-adaptive manner to combine an anchor and multiple negatives for HNG. Compared to current methods, GCA-HNG allows perceiving sample correlations with numerous negatives from a global and comprehensive perspective and generates the negatives with better hardness and diversity. Extensive experiment results demonstrate that the proposed GCA-HNG is superior to related methods on four image retrieval benchmark datasets.

硬负生成旨在生成信息丰富的负样本，有助于确定决策边界，从而促进推进深度度量学习。当前工作选择对/三重样本，学习它们的相关性，并将它们融合以生成硬底片。然而，这些工作只考虑了所选样本的局部相关性，而忽略了全局样本相关性，这些相关性会提供更重要的信息以产生更多信息的负面信息。在这项工作中，我们提出了一个全局相关性感知的硬负值生成 （GCA-HNG） 框架，该框架首先从全球角度学习样本相关性，并利用这些相关性来指导生成硬度自适应和多样化的负值。具体来说，这种方法首先构建一个结构化图来对样本相关性进行建模，其中每个节点代表一个特定的样本，每条边代表相应样本之间的相关性。然后，我们引入迭代图消息传播，将 node 和 edge 的消息传播到整个图中，从而全局学习样本相关性。最后，在学习到的全局相关性的指导下，我们提出了一种通道自适应方式，将锚点和多个负数结合起来进行 HNG。与目前的方法相比，GCA-HNG 可以从全局和全面的角度感知样品与众多负片的相关性，并生成具有更好硬度和多样性的负片。大量的实验结果表明，所提出的 GCA-HNG 在 4 个图像检索基准数据集上优于相关方法。