论文标题
研究时间内变异性在时间结合中的影响
Investigating the Effect of Intraclass Variability in Temporal Ensembling
论文作者
论文摘要
时间结合是一种半监督的方法，它允许训练具有少量标记图像的深神经网络模型。在本文中，我们介绍了有关类内变异性对时间结合的影响的初步研究，分别侧重于种子大小和种子类型。通过我们的实验，我们发现（a）数据集的准确性显着下降，这些数据集具有高度的内部变异性，（b）更多的种子图像在整个数据集中提供了持续更高的精度，并且（c）种子类型确实会影响整体效率，在那里它产生了越来越高的准确性。此外，根据我们的实验，我们还发现KMNIST是时间结合的竞争基线。
Temporal Ensembling is a semi-supervised approach that allows training deep neural network models with a small number of labeled images. In this paper, we present our preliminary study on the effect of intraclass variability on temporal ensembling, with a focus on seed size and seed type, respectively. Through our experiments we find that (a) there is a significant drop in accuracy with datasets that offer high intraclass variability, (b) more seed images offer consistently higher accuracy across the datasets, and (c) seed type indeed has an impact on the overall efficiency, where it produces a spectrum of accuracy both lower and higher. Additionally, based on our experiments, we also find KMNIST to be a competitive baseline for temporal ensembling.
