Learning to hash pictures a list-wise sorting problem. Its testing metrics, e.g., mean-average precision, count on a sorted candidate list ordered by pair-wise code similarity. However, scarcely does one train a deep hashing model with the sorted results end-to-end because of the non-differentiable nature of the sorting operation. This inconsistency in the objectives of training and test may lead to sub-optimal performance since the training loss often fails to reflect the actual retrieval metric. In this paper, we tackle this problem by introducing Naturally-Sorted Hashing (NSH). We sort the Hamming distances of samples' hash codes and accordingly gather their latent representations for self-supervised training. Thanks to the recent advances in differentiable sorting approximations, the hash head receives gradients from the sorter so that the hash encoder can be optimized along with the training procedure. Additionally, we describe a novel Sorted Noise-Contrastive Estimation (SortedNCE) loss that selectively picks positive and negative samples for contrastive learning, which allows NSH to mine data semantic relations during training in an unsupervised manner. Our extensive experiments show the proposed NSH model significantly outperforms the existing unsupervised hashing methods on three benchmarked datasets.

翻译：学习以 shash 绘制列表排序问题 。 它的测试量度, 例如平均精确度, 依靠按对称代码相似性排序的分类候选名单 。 但是, 由于排序操作的分类性质没有差异, 很少用分解结果端到端。 培训和测试目标的这种不一致可能导致亚最佳性能, 因为培训损失往往不能反映实际的检索度量。 在本文中, 我们通过引入自然 Sorted Hashing( NSH) 来解决这个问题。 我们排序样本的仓储距离, 并相应地收集它们潜在的自我监督培训演示。 由于最近在可分类结果端端到端之间出现的进展, 仓头从排序器得到的梯度, 以便可以优化导出导出导出导出器的导出器与培训程序。 此外, 我们描述了一个新颖的节制噪调调 Estitive Estimation (SordedNCE) 损失, 在非选择性地选择正面和负式的样本中, 在对比性测试的现有数据实验中, 能够让NSH 显示现有数据模型的深度校正式校准式校准式校正式校正式校正关系。