arXiv research

Proposes a new model for unsupervised clustering with latent variables.

A new method generates meta-tasks using generative models for unsupervised learning.

Unsupervised pre-training improves model generalization, but lacks theoretical understanding.

Diffusion models enhance speech without supervision.

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

TGLS generates text by optimizing search results and learning from them.

This paper proves the theoretical advantage of unsupervised pretraining for machine learning tasks.

This research shows unsupervised GANs can perform object segmentation without labels.

BigBiGAN improves unsupervised representation learning using image generation quality.

Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervis…

This paper develops a federated EM algorithm for unsupervised learning of mixture models.

Unsupervised RNNGs perform similarly to supervised ones in language modeling and grammar induction.

A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations us…

For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learnin…

Proposes manifold-based unsupervised anomaly detection for visual data.

A new method combines generative and feature-based approaches for unsupervised anomaly detection.

We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able to learn from training data of this type are potentially of great use as many real-world datasets ar…

New model combines ICA and HMM for unsupervised learning of nonstationary time series.

SuTaT creates dialogue summaries for tete-a-tetes without labeled data.

LCBM model improves image classification without human supervision.

Proposes DC3-GAN for diverse unsupervised conditional generation.

Develops a new unsupervised clustering method using Variational Information Bottleneck and Gaussian Mixture Model.

Unsupervised image inpainting models generate plausible reconstructions from incomplete data.

Improved disentanglement of data factors using recursive training.

Score calibration enables automatic speaker recognizers to make cost-effective accept / reject decisions. Traditional calibration requires supervised data, which is an expensive resource. We propose a 2-component GMM for unsupervised calibration and demonstrate good performance relative to a supervised baseline on NIST…

SUOD accelerates unsupervised outlier detection for large datasets.

We give a novel formal theoretical framework for unsupervised learning with two distinctive characteristics. First, it does not assume any generative model and based on a worst-case performance metric. Second, it is comparative, namely performance is measured with respect to a given hypothesis class. This allows to avo…

Unified framework for unsupervised concept extraction simplifies guarantees.

Unified model explains AT's generative ability.

Study finds unsupervised imputation before cross-validation can reduce computational costs without significantly degrading model performance.

SUPER learning combines supervised and unsupervised methods for LDCT image reconstruction.

Proposes RN for unsupervised attention in neural networks.

Unsupervised learning models can produce accurate but misleading predictions.

Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for…

Paper proposes a new unsupervised clustering method using attention models.

Generative models predict page quality without training, useful for low-resource settings.

Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysi…

Unsupervised learning models can be indistinguishable without identifiability, leading to unreliable representations.

PhyloVAE learns tree topologies without supervision.

Novel unsupervised random forests improve density estimation and data synthesis.

This work addresses encoding biases in neural networks by tailoring models with unsupervised losses.

Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This pape…

In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM). In the multi-clustering integration module, we apply three unsupervised K-means, affinity propagation and spectral c…

Unsupervised deep learning detects image quality issues without annotations.

We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself i…

Novel unsupervised audio source separation using generative priors.

Unsupervised mesh disentanglement separates identity and pose.

Few-shot unsupervised image-to-image translation model learns from a few examples.