论文标题
平滑ap：平滑通往大型图像检索的路径
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
论文作者
论文摘要
优化基于排名的度量，例如平均精度（AP），由于它是不可差异的事实，因此臭名昭著，因此无法使用梯度降低方法直接优化。为此，我们引入了一个目标，该目标优化了AP的平滑近似值，即平滑-AP。 Smooth-AP是一个插件的目标功能，可以通过简单而优雅的实现对深层网络进行端到端的培训。我们还提供了一个分析，说明为什么直接优化基于排名的AP指标提供了比其他深度度量学习损失的好处。我们对标准检索基准进行了平滑-AP：斯坦福在线产品和车辆，并在大规模数据集上进行评估：inaturalist for Fine Graining类别检索，而VGGFACE2和IJB-C进行面部检索。在所有情况下，我们都会改善最先进的性能，尤其是对于大型数据集，从而证明了平滑-AP对现实世界情景的有效性和可扩展性。
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an objective that optimises instead a smoothed approximation of AP, coined Smooth-AP. Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation. We also present an analysis for why directly optimising the ranking based metric of AP offers benefits over other deep metric learning losses. We apply Smooth-AP to standard retrieval benchmarks: Stanford Online products and VehicleID, and also evaluate on larger-scale datasets: INaturalist for fine-grained category retrieval, and VGGFace2 and IJB-C for face retrieval. In all cases, we improve the performance over the state-of-the-art, especially for larger-scale datasets, thus demonstrating the effectiveness and scalability of Smooth-AP to real-world scenarios.
