论文标题
用于无监督图像分类的伪标签自动编码器
A Pseudo-labelling Auto-Encoder for unsupervised image classification
论文作者
论文摘要
在本文中，我们介绍了denoising自动编码器的独特变体，并将其与感知损失相结合，以无监督的方式对图像进行分类。所提出的称为伪标记的方法包括首先在每个训练图像上应用一组随机采样的数据增强转换。结果，每个初始图像都可以视为其相应增强图像的伪标记。然后，使用自动编码器来学习每组增强图像及其相应的伪标签之间的映射。此外，采用感知损失来考虑图像同一邻域中像素之间的现有依赖关系。这种组合鼓励编码器输出更丰富的编码，这些编码对输入类别非常有用。因此，自动编码器在所有测试数据集的稳定性，准确性和一致性方面都提高了自动编码器在无监督图像分类上的性能。 MNIST，CIFAR-10和SVHN数据集的先前最先进的精度分别提高了0.3 \％，3.11 \％和9.21 \％。
In this paper, we introduce a unique variant of the denoising Auto-Encoder and combine it with the perceptual loss to classify images in an unsupervised manner. The proposed method, called Pseudo Labelling, consists of first applying a randomly sampled set of data augmentation transformations to each training image. As a result, each initial image can be considered as a pseudo-label to its corresponding augmented ones. Then, an Auto-Encoder is used to learn the mapping between each set of the augmented images and its corresponding pseudo-label. Furthermore, the perceptual loss is employed to take into consideration the existing dependencies between the pixels in the same neighbourhood of an image. This combination encourages the encoder to output richer encodings that are highly informative of the input's class. Consequently, the Auto-Encoder's performance on unsupervised image classification is improved in terms of stability, accuracy and consistency across all tested datasets. Previous state-of-the-art accuracy on the MNIST, CIFAR-10 and SVHN datasets is improved by 0.3\%, 3.11\% and 9.21\% respectively.
