Related papers: LSD-C: Linearly Separable Deep Clusters

Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of labeled samples and perform data augmentation on unlabeled…

Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover…

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…

The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths. If these challenges are not properly handled, the resulting…

In novel class discovery (NCD), we are given labeled data from seen classes and unlabeled data from unseen classes, and we train clustering models for the unseen classes. However, the implicit assumptions behind NCD are still unclear. In…

Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and clustering within an iterative framework. However, the rise…

The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…

The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic…

Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the…

High-dimensional clustering analysis is a challenging problem in statistics and machine learning, with broad applications such as the analysis of microarray data and RNA-seq data. In this paper, we propose a new clustering procedure called…

In the face of complex natural images, existing deep clustering algorithms fall significantly short in terms of clustering accuracy when compared to supervised classification methods, making them less practical. This paper introduces an…

Clustering high-dimensional data is a critical challenge in machine learning due to the curse of dimensionality and the presence of noise. Traditional clustering algorithms often fail to capture the intrinsic structures in such data. This…

Noisy label learning aims to train deep neural networks using a large amount of samples with noisy labels, whose main challenge comes from how to deal with the inaccurate supervision caused by wrong labels. Existing works either take the…

We consider the unsupervised learning problem of assigning labels to unlabeled data. A naive approach is to use clustering methods, but this works well only when data is properly clustered and each cluster corresponds to an underlying…

Feature selection methods have an important role on the readability of data and the reduction of complexity of learning algorithms. In recent years, a variety of efforts are investigated on feature selection problems based on unsupervised…

Deep subspace clustering (DSC) algorithms face several challenges that hinder their widespread adoption across variois application domains. First, clustering quality is typically assessed using only the encoder's output layer, disregarding…

The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting…

Unsupervised person re-identification (Re-ID) attracts increasing attention due to its potential to resolve the scalability problem of supervised Re-ID models. Most existing unsupervised methods adopt an iterative clustering mechanism,…

Medical image analysis using supervised deep learning methods remains problematic because of the reliance of deep learning methods on large amounts of labelled training data. Although medical imaging data repositories continue to expand…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…