A Pseudo-labelling Auto-Encoder for unsupervised image classification

TL;DR

This paper presents a novel unsupervised image classification method combining a pseudo-labeling auto-encoder with perceptual loss, improving accuracy and stability over previous methods across multiple datasets.

Contribution

Introduces a pseudo-labeling auto-encoder with perceptual loss for unsupervised image classification, enhancing performance and stability.

Findings

Improved accuracy on MNIST, CIFAR-10, SVHN datasets.

Enhanced stability and consistency in classification.

Achieved state-of-the-art results with small accuracy gains.

Abstract

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.