Unsupervised Image Classification
21 papers with code • 7 benchmarks • 6 datasets
Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels.
Image credit: ImageNet clustering results of SCAN: Learning to Classify Images without Labels (ECCV 2020)
LibrariesUse these libraries to find Unsupervised Image Classification models and implementations
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.
In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution.
Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms.
The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.
Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model.
Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation.
Combining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way.
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets.
In this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.