TL;DR利用 pair-wise loss 进行度量学习可以通过梯度分解来统一当前的损失函数,并明确构建配对梯度更新,以最大程度地提高对图像数据集的检索精度。
Abstract
pair-wise loss is an approach to metric learning that learns a semantic
embedding by optimizing a loss function that encourages images from the same
semantic class to be mapped closer than images from different c