标题： 自监督孪生自编码器 显示英文标题

标题： Self-Supervised Siamese Autoencoders

摘要： 完全监督模型通常需要大量标记的训练数据，这往往成本高昂且难以获取。 相比之下，自监督表示学习减少了达到相同甚至更高下游性能所需的标记数据量。 目标是在一个自监督任务上预训练深度神经网络，以便之后网络能够从原始输入数据中提取有意义的特征。 这些特征随后被用作下游任务（如图像分类）的输入。 以前，自动编码器和孪生网络（如SimSiam）已被成功应用于这些任务。 然而，仍存在一些挑战，例如将特征的特性（例如细节水平）与给定的任务和数据集相匹配。 在本文中，我们提出了一种新的自监督方法，结合了孪生架构和去噪自动编码器的优点。 我们表明，我们的模型称为SidAE（孪生去噪自动编码器），在多个数据集、设置和场景中优于两种自监督基线。 关键的是，这包括只有少量标记数据可用的情况。 显示英文摘要

摘要： Fully supervised models often require large amounts of labeled training data, which tends to be costly and hard to acquire. In contrast, self-supervised representation learning reduces the amount of labeled data needed for achieving the same or even higher downstream performance. The goal is to pre-train deep neural networks on a self-supervised task such that afterwards the networks are able to extract meaningful features from raw input data. These features are then used as inputs in downstream tasks, such as image classification. Previously, autoencoders and Siamese networks such as SimSiam have been successfully employed in those tasks. Yet, challenges remain, such as matching characteristics of the features (e.g., level of detail) to the given task and data set. In this paper, we present a new self-supervised method that combines the benefits of Siamese architectures and denoising autoencoders. We show that our model, called SidAE (Siamese denoising autoencoder), outperforms two self-supervised baselines across multiple data sets, settings, and scenarios. Crucially, this includes conditions in which only a small amount of labeled data is available.