Variational Autoencoders For Semi-Supervised Deep Metric Learning
Variational Autoencoders For Semi-Supervised Deep Metric Learning
复制标题
DOI：
10.25080/majora-212e5952-022
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Nathan Safir;Meekail Zain;C. Godwin;Eric L. Miller;Bella Humphrey;Shannon Quinn
中科院分区：
文献类型：
--
作者：
Nathan Safir;Meekail Zain;C. Godwin;Eric L. Miller;Bella Humphrey;Shannon Quinn
深度度量学习（DML）方法通常不包含未标记的数据。我们建议借用变分自动编码器（VAE）方法的组件来扩展DML方法，以在半监督数据集上进行训练。我们通过实验评估了在VAE潜在空间上执行DML的原子贝内，例如使用未标记数据进行训练的增强能力以及在先验知识下诱导偏差的能力。我们发现，使用自动编码器和VAE联合训练DML可能对一些半超预期数据集有潜在的帮助，但是在DML损失和跨时期的额外无监督损失之间交替的训练例程通常是不可行的。
—Deep metric learning (DML) methods generally do not incorporate unlabelled data. We propose borrowing components of the variational autoen-coder (VAE) methodology to extend DML methods to train on semi-supervised datasets. We experimentally evaluate the atomic benefits to the performing DML on the VAE latent space such as the enhanced ability to train using unlabelled data and to induce bias given prior knowledge. We find that jointly training DML with an autoencoder and VAE may be potentially helpful for some semi-suprevised datasets, but that a training routine of alternating between the DML loss and an additional unsupervised loss across epochs is generally unviable.