论文标题
没有标签的自学成才的公制学习
Self-Taught Metric Learning without Labels
论文作者
论文摘要
我们为无监督的度量学习提供了一个新颖的自学成才框架，该框架通过嵌入模型的移动平均值来预测数据之间的类等价关系与以预测关系为伪标签，在数据之间进行了交替。我们框架的核心是一种算法，该算法研究了有关嵌入空间的数据环境，以预测其阶级等效关系为伪标签。该算法可实现有效的端到端培训，因为它不需要伪造的伪标记模块。此外，阶级等价关系为学习嵌入空间提供了丰富的监督信号。在用于公制学习的标准基准上，它显然优于现有的无监督学习方法，有时甚至使用相同的骨干网络击败监督的学习模型。它也适用于半监督指标学习，作为利用其他未标记数据的一种方式，并通过大大提高监督学习的绩效来实现最新技术。
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted relations as pseudo labels. At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels. The algorithm enables efficient end-to-end training since it demands no off-the-shelf module for pseudo labeling. Also, the class-equivalence relations provide rich supervisory signals for learning an embedding space. On standard benchmarks for metric learning, it clearly outperforms existing unsupervised learning methods and sometimes even beats supervised learning models using the same backbone network. It is also applied to semi-supervised metric learning as a way of exploiting additional unlabeled data, and achieves the state of the art by boosting performance of supervised learning substantially.
