论文标题
对比度学习中的图像表示形式
Partitioning Image Representation in Contrastive Learning
论文作者
论文摘要
相比之下，图像域中的对比学习，锚定样品被迫具有尽可能近的表示。但是，强迫两个样本具有相同的表示可能会产生误导，因为数据增强技术使两个样本不同。在本文中，我们介绍了一个新的表示，分区的表示，可以在对比学习中学习锚和正面样本的共同和独特的特征。分区表示由两个部分组成：内容部分和样式部分。内容零件代表类的常见特征，样式部分代表每个样本的自己的特征，这可以导致表示数据增强方法的表示。我们可以通过将对比度学习的损失函数分别分别为两个单独的表示形式，仅将对比度学习的损失函数分解为两个术语，从而实现分区的表示。为了通过两个部分评估我们的表示形式，我们采用了两个框架模型：变化自动编码器（VAE）和Bootstrapyour自己的潜在（BYOL）以显示内容和样式的可分离性，并分别确认分类中的概括能力。基于实验，我们表明我们的方法可以在VAE框架中分离两种类型的信息，并在线性可分离性中优于常规BYOL，并且是下游任务的一些射击学习任务。
In contrastive learning in the image domain, the anchor and positive samples are forced to have as close representations as possible. However, forcing the two samples to have the same representation could be misleading because the data augmentation techniques make the two samples different. In this paper, we introduce a new representation, partitioned representation, which can learn both common and unique features of the anchor and positive samples in contrastive learning. The partitioned representation consists of two parts: the content part and the style part. The content part represents common features of the class, and the style part represents the own features of each sample, which can lead to the representation of the data augmentation method. We can achieve the partitioned representation simply by decomposing a loss function of contrastive learning into two terms on the two separate representations, respectively. To evaluate our representation with two parts, we take two framework models: Variational AutoEncoder (VAE) and BootstrapYour Own Latent(BYOL) to show the separability of content and style, and to confirm the generalization ability in classification, respectively. Based on the experiments, we show that our approach can separate two types of information in the VAE framework and outperforms the conventional BYOL in linear separability and a few-shot learning task as downstream tasks.
