论文标题
自我监督学习中的表示不确定性作为变异推理
Representation Uncertainty in Self-Supervised Learning as Variational Inference
论文作者
论文摘要
在这项研究中，提出了一种新颖的自我监督学习（SSL）方法，该方法考虑了SSL的变化推断，不仅要学习表示，而且还要学习不确定性。 SSL是一种学习表示形式的方法，而无需标记，通过最大程度地提高图像不同增强视图的图像表示之间的相似性。同时，变异自动编码器（VAE）是一种无监督的表示学习方法，它训练具有变异推理的概率生成模型。 VAE和SSL都可以在没有标签的情况下学习表示形式，但是过去并未对其关系进行研究。在此，已经阐明了SSL与变异推理之间的理论关系。此外，已经提出了一种新颖的方法，即simsiam（vi-simsiam）。 VI-SIMSIAM可以通过用变异推理解释Simsiam并定义潜在空间分布来预测表示不确定性。本实验定性地表明，Vi-Simsiam可以通过比较输入图像和预测不确定性来学习不确定性。此外，我们描述了估计的不确定性和分类精度之间的关系。
In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties. SSL is a method of learning representations without labels by maximizing the similarity between image representations of different augmented views of an image. Meanwhile, variational autoencoder (VAE) is an unsupervised representation learning method that trains a probabilistic generative model with variational inference. Both VAE and SSL can learn representations without labels, but their relationship has not been investigated in the past. Herein, the theoretical relationship between SSL and variational inference has been clarified. Furthermore, a novel method, namely variational inference SimSiam (VI-SimSiam), has been proposed. VI-SimSiam can predict the representation uncertainty by interpreting SimSiam with variational inference and defining the latent space distribution. The present experiments qualitatively show that VI- SimSiam could learn uncertainty by comparing input images and predicted uncertainties. Additionally, we described a relationship between estimated uncertainty and classification accuracy.
