Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models. Despite years of effort, direct optimization for these metrics remains a challenge due to their non-differentiable and non-decomposable nature. We present an efficient, theoretically sound, and general method for differentiating rank-based metrics with mini-batch gradient descent. In addition, we address optimization instability and sparsity of the supervision signal that both arise from using rank-based metrics as optimization targets. Resulting losses based on recall and Average Precision are applied to image retrieval and object detection tasks. We obtain performance that is competitive with state-of-the-art on standard image retrieval datasets and consistently improve performance of near state-of-the-art object detectors.

针对计算机视觉模型的性能评估中常用的排名度量标准由于其不可微和不可分解的特性而直接优化仍然存在挑战。本研究提出了一种高效、有理论支持且通用的方法，使用小批量梯度下降来区分排名度量标准，并解决使用排名度量标准作为优化目标所导致的优化不稳定性和监督信号的稀疏性问题。基于召回率和平均精度的损失被应用于图像检索和目标检测任务中，取得了与标准图像检索数据集上的最先进性能相竞争，并在接近最先进的目标检测器上始终提高性能。

使用黑盒微分优化基于排名的评估指标