In recent years, models based on Graph Convolutional Networks (GCN) have made significant strides in the field of graph data analysis. However, challenges such as over-smoothing and over-compression remain when handling large-scale and complex graph datasets, leading to a decline in clustering quality. Although the Graph Transformer architecture has mitigated some of these issues, its performance is still limited when processing heterogeneous graph data. To address these challenges, this study proposes a novel deep clustering framework that comprising GCN, Autoencoder (AE), and Graph Transformer, termed the Tri-Learn Graph Fusion Network (Tri-GFN). This framework enhances the differentiation and consistency of global and local information through a unique tri-learning mechanism and feature fusion enhancement strategy. The framework integrates GCN, AE, and Graph Transformer modules. These components are meticulously fused by a triple-channel enhancement module, which maximizes the use of both node attributes and topological structures, ensuring robust clustering representation. The tri-learning mechanism allows mutual learning among these modules, while the feature fusion strategy enables the model to capture complex relationships, yielding highly discriminative representations for graph clustering. It surpasses many state-of-the-art methods, achieving an accuracy improvement of approximately 0.87% on the ACM dataset, 14.14 % on the Reuters dataset, and 7.58 % on the USPS dataset. Due to its outstanding performance on the Reuters dataset, Tri-GFN can be applied to automatic news classification, topic retrieval, and related fields.
This research implements an advanced unsupervised clustering system for MNIST handwritten digits through two-phase deep autoencoder architecture. A deep neural autoencoder requires a training process during phase one to develop minimal yet interpretive representations of images by minimizing reconstruction errors. During the second phase we unify the reconstruction error with a KMeans clustering loss for learned latent embeddings through a joint distance-based objective. Our model contains three elements which include batch normalization combined with dropout and weight decay for achieving generalized and stable results. The framework achieves superior clustering performance during extensive tests which used intrinsic measurements including Silhouette Score and Davies-Bouldin Index coupled with extrinsic metrics NMI and ARI when processing image features. The research uses t-SNE visualization to present learned embeddings that show distinct clusters for digits. Our approach reaches an optimal combination between data reconstruction accuracy and cluster separation purity when adding the benefit of understandable results and scalable implementations. The approach creates a dependable base that helps deploy unsupervised representation learning in different large-scale image clustering applications.
In recent years the wide availability of high-resolution radar satellite images along with the advancement of computer vision models have enabled the remote monitoring of the surface area of wetlands. However, these models require large amounts of manually annotated satellite images, which are slow and expensive to produce. To overcome this problem, self-supervised training methods have been deployed to train models without using annotated data. In this paper we use a combination of deep clustering and negative sampling to train a model to segment radar satellite images into areas that separate water from land without the use of any manual annotations. Furthermore, we implement an ensemble version of the model to reduce variance and improve performance. Compared to a single fully-supervised model using the same architecture, our ensemble of self-supervised models achieves a 0.02 improvement in the Intersection Over Union metric over our test dataset.
To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in what can be perceived as ``cohesive properties''. Therefore, hypotheses on the nature of clusters must be set: they can be either generative or discriminative. As the last decade witnessed the impressive growth of deep clustering methods that involve neural networks to handle high-dimensional data often in a discriminative manner; we concentrate mainly on the discriminative hypotheses. In this paper, our aim is to provide an accessible historical perspective on the evolution of discriminative clustering methods and notably how the nature of assumptions of the discriminative models changed over time: from decision boundaries to invariance critics. We notably highlight how mutual information has been a historical cornerstone of the progress of (deep) discriminative clustering methods. We also show some known limitations of mutual information and how discriminative clustering methods tried to circumvent those. We then discuss the challenges that discriminative clustering faces with respect to the selection of the number of clusters. Finally, we showcase these techniques using the dedicated Python package, GemClus, that we have developed for discriminative clustering.
Raman spectroscopy serves as a powerful and reliable tool for analyzing the chemical information of substances. The integration of Raman spectroscopy with deep learning methods enables rapid qualitative and quantitative analysis of materials. Most existing approaches adopt supervised learning methods. Although supervised learning has achieved satisfactory accuracy in spectral analysis, it is still constrained by costly and limited well-annotated spectral datasets for training. When spectral annotation is challenging or the amount of annotated data is insufficient, the performance of supervised learning in spectral material identification declines. In order to address the challenge of feature extraction from unannotated spectra, we propose a self-supervised learning paradigm for Raman Spectroscopy based on a Masked AutoEncoder, termed SMAE. SMAE does not require any spectral annotations during pre-training. By randomly masking and then reconstructing the spectral information, the model learns essential spectral features. The reconstructed spectra exhibit certain denoising properties, improving the signal-to-noise ratio (SNR) by more than twofold. Utilizing the network weights obtained from masked pre-training, SMAE achieves clustering accuracy of over 80% for 30 classes of isolated bacteria in a pathogenic bacterial dataset, demonstrating significant improvements compared to classical unsupervised methods and other state-of-the-art deep clustering methods. After fine-tuning the network with a limited amount of annotated data, SMAE achieves an identification accuracy of 83.90% on the test set, presenting competitive performance against the supervised ResNet (83.40%).
Autoencoders offer a general way of learning low-dimensional, non-linear representations from data without labels. This is achieved without making any particular assumptions about the data type or other domain knowledge. The generality and domain agnosticism in combination with their simplicity make autoencoders a perfect sandbox for researching and developing novel (deep) clustering algorithms. Clustering methods group data based on similarity, a task that benefits from the lower-dimensional representation learned by an autoencoder, mitigating the curse of dimensionality. Specifically, the combination of deep learning with clustering, called Deep Clustering, enables to learn a representation tailored to specific clustering tasks, leading to high-quality results. This survey provides an introduction to fundamental autoencoder-based deep clustering algorithms that serve as building blocks for many modern approaches.
Martian terrain recognition is pivotal for advancing our understanding of topography, geomorphology, paleoclimate, and habitability. While deep clustering methods have shown promise in learning semantically homogeneous feature embeddings from Martian rover imagery, the natural variations in intensity, scale, and rotation pose significant challenges for accurate terrain classification. To address these limitations, we propose Deep Constrained Clustering with Metric Learning (DCCML), a novel algorithm that leverages multiple constraint types to guide the clustering process. DCCML incorporates soft must-link constraints derived from spatial and depth similarities between neighboring patches, alongside hard constraints from stereo camera pairs and temporally adjacent images. Experimental evaluation on the Curiosity rover dataset (with 150 clusters) demonstrates that DCCML increases homogeneous clusters by 16.7 percent while reducing the Davies-Bouldin Index from 3.86 to 1.82 and boosting retrieval accuracy from 86.71 percent to 89.86 percent. This improvement enables more precise classification of Martian geological features, advancing our capacity to analyze and understand the planet's landscape.
We propose a novel approach for optimizing the graph ratio-cut by modeling the binary assignments as random variables. We provide an upper bound on the expected ratio-cut, as well as an unbiased estimate of its gradient, to learn the parameters of the assignment variables in an online setting. The clustering resulting from our probabilistic approach (PRCut) outperforms the Rayleigh quotient relaxation of the combinatorial problem, its online learning extensions, and several widely used methods. We demonstrate that the PRCut clustering closely aligns with the similarity measure and can perform as well as a supervised classifier when label-based similarities are provided. This novel approach can leverage out-of-the-box self-supervised representations to achieve competitive performance and serve as an evaluation method for the quality of these representations.
Brain nuclei are clusters of anatomically distinct neurons that serve as important hubs for processing and relaying information in various neural circuits. Fine-scale parcellation of the brain nuclei is vital for a comprehensive understanding of its anatomico-functional correlations. Diffusion MRI tractography is an advanced imaging technique that can estimate the brain's white matter structural connectivity to potentially reveal the topography of the nuclei of interest for studying its subdivisions. In this work, we present a deep clustering pipeline, namely DeepNuParc, to perform automated, fine-scale parcellation of brain nuclei using diffusion MRI tractography. First, we incorporate a newly proposed deep learning approach to enable accurate segmentation of the nuclei of interest directly on the dMRI data. Next, we design a novel streamline clustering-based structural connectivity feature for a robust representation of voxels within the nuclei. Finally, we improve the popular joint dimensionality reduction and k-means clustering approach to enable nuclei parcellation at a finer scale. We demonstrate DeepNuParc on two important brain structures, i.e. the amygdala and the thalamus, that are known to have multiple anatomically and functionally distinct nuclei subdivisions. Experimental results show that DeepNuParc enables consistent parcellation of the nuclei into multiple parcels across multiple subjects and achieves good correspondence with the widely used coarse-scale atlases. Our codes are available at https://github.com/HarlandZZC/deep_nuclei_parcellation.
The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give rise to three primary issues. The joint training causes Feature Randomness and Feature Drift, whereas the independent training causes Feature Randomness and Feature Twist. In essence, using pseudo-labels generates random and unreliable features. The combination of pseudo-supervision and self-supervision drifts the reliable clustering-oriented features. Moreover, moving from self-supervision to pseudo-supervision can twist the curved latent manifolds. This paper addresses the limitations of existing deep clustering paradigms concerning Feature Randomness, Feature Drift, and Feature Twist. We propose a new paradigm with a new strategy that replaces pseudo-supervision with a second round of self-supervision training. The new strategy makes the transition between instance-level self-supervision and neighborhood-level self-supervision smoother and less abrupt. Moreover, it prevents the drifting effect that is caused by the strong competition between instance-level self-supervision and clustering-level pseudo-supervision. Moreover, the absence of the pseudo-supervision prevents the risk of generating random features. With this novel approach, our paper introduces a Rethinking of the Deep Clustering Paradigms, denoted by R-DC. Our model is specifically designed to address three primary challenges encountered in Deep Clustering: Feature Randomness, Feature Drift, and Feature Twist. Experimental results conducted on six datasets have shown that the two-level self-supervision training yields substantial improvements.
Although multi-view learning has achieved remarkable progress over the past decades, most existing methods implicitly assume that all views (or modalities) are well-aligned. In practice, however, collecting fully aligned views is challenging due to complexities and discordances in time and space, resulting in the Partially View-unaligned Problem (PVP), such as audio-video asynchrony caused by network congestion. While some methods are proposed to align the unaligned views by learning view-invariant representations, almost all of them overlook specific information across different views for complementarity, limiting performance improvement. To address these problems, we propose a robust framework, dubbed VariatIonal ConTrAstive Learning (VITAL), designed to learn both common and specific information simultaneously. To be specific, each data sample is first modeled as a Gaussian distribution in the latent space, where the mean estimates the most probable common information, while the variance indicates view-specific information. Second, by using variational inference, VITAL conducts intra- and inter-view contrastive learning to preserve common and specific semantics in the distribution representations, thereby achieving comprehensive perception. As a result, the common representation (mean) could be used to guide category-level realignment, while the specific representation (variance) complements sample semantic information, thereby boosting overall performance. Finally, considering the abundance of False Negative Pairs (FNPs) generated by unsupervised contrastive learning, we propose a robust loss function that seamlessly incorporates FNP rectification into the contrastive learning paradigm. Empirical evaluations on eight benchmark datasets reveal that VITAL outperforms ten state-of-the-art deep clustering baselines, demonstrating its efficacy in both partially and fully aligned scenarios. The Code is available at https://github.com/He-Changhao/2024-MM-VITAL.
Many competitive clustering pipelines have a multi-modal design, leveraging large language models (LLMs) or other text encoders, and text-image pairs, which are often unavailable in real-world downstream applications. Additionally, such frameworks are generally complicated to train and require substantial computational resources, making widespread adoption challenging. In this work, we show that in deep clustering, competitive performance with more complex state-of-the-art methods can be achieved using a text-free and highly simplified training pipeline. In particular, our approach, Simple Clustering via Pre-trained models (SCP), trains only a small cluster head while leveraging pre-trained vision model feature representations and positive data pairs. Experiments on benchmark datasets including CIFAR-10, CIFAR-20, CIFAR-100, STL-10, ImageNet-10, and ImageNet-Dogs, demonstrate that SCP achieves highly competitive performance. Furthermore, we provide a theoretical result explaining why, at least under ideal conditions, additional text-based embeddings may not be necessary to achieve strong clustering performance in vision.
Auscultation plays a pivotal role in early respiratory and pulmonary disease diagnosis. Despite the emergence of deep learning-based methods for automatic respiratory sound classification post-Covid-19, limited datasets impede performance enhancement. Distinguishing between normal and abnormal respiratory sounds poses challenges due to the coexistence of normal respiratory components and noise components in both types. Moreover, different abnormal respiratory sounds exhibit similar anomalous features, hindering their differentiation. Besides, existing state-of-the-art models suffer from excessive parameter size, impeding deployment on resource-constrained mobile platforms. To address these issues, we design a lightweight network CycleGuardian and propose a framework based on an improved deep clustering and contrastive learning. We first generate a hybrid spectrogram for feature diversity and grouping spectrograms to facilitating intermittent abnormal sound capture.Then, CycleGuardian integrates a deep clustering module with a similarity-constrained clustering component to improve the ability to capture abnormal features and a contrastive learning module with group mixing for enhanced abnormal feature discernment. Multi-objective optimization enhances overall performance during training. In experiments we use the ICBHI2017 dataset, following the official split method and without any pre-trained weights, our method achieves Sp: 82.06 $\%$, Se: 44.47$\%$, and Score: 63.26$\%$ with a network model size of 38M, comparing to the current model, our method leads by nearly 7$\%$, achieving the current best performances. Additionally, we deploy the network on Android devices, showcasing a comprehensive intelligent respiratory sound auscultation system.
We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the Expectation-Maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between updating model parameters by maximizing the Evidence Lower Bound (ELBO) of the log-likelihood and refining cluster assignments based on the learned distributions. This enables effective clustering and generation of new samples from each cluster. Unlike existing VAE-based methods, our approach eliminates the need for a Gaussian Mixture Model (GMM) prior or additional regularization techniques. Experiments on MNIST and FashionMNIST demonstrate superior clustering performance compared to state-of-the-art methods.
Deep clustering is an essential task in modern artificial intelligence, aiming to partition a set of data samples into a given number of homogeneous groups (i.e., clusters). Even though many Deep Neural Network (DNN) backbones and clustering strategies have been proposed for the task, achieving increasingly improved performance, deep clustering remains very challenging due to the lack of accurately labeled samples. In this paper, we propose a novel approach of deep clustering via community detection. It initializes clustering by detecting many communities, and then gradually expands clusters by community merging. Compared with the existing clustering strategies, community detection factors in the new perspective of cluster network analysis. As a result, it has the inherent benefit of high pseudo-label purity, which is critical to the performance of self-supervision. We have validated the efficacy of the proposed approach on benchmark image datasets. Our extensive experiments have shown that it can effectively improve the SOTA performance. Our ablation study also demonstrates that the new network perspective can effectively improve community pseudo-label purity, resulting in improved clustering performance.
Large scale Bayesian nonparametrics (BNP) learner such as stochastic variational inference (SVI) can handle datasets with large class number and large training size at fractional cost. Like its predecessor, SVI rely on the assumption of conjugate variational posterior to approximate the true posterior. A more challenging problem is to consider large scale learning on non-conjugate posterior. Recent works in this direction are mostly associated with using Monte Carlo methods for approximating the learner. However, these works are usually demonstrated on non-BNP related task and less complex models such as logistic regression, due to higher computational complexity. In order to overcome the issue faced by SVI, we develop a novel approach based on the recently proposed variational maximization-maximization (VMM) learner to allow large scale learning on non-conjugate posterior. Unlike SVI, our VMM learner does not require closed-form expression for the variational posterior expectatations. Our only requirement is that the variational posterior is differentiable. In order to ensure convergence in stochastic settings, SVI rely on decaying step-sizes to slow its learning. Inspired by SVI and Adam, we propose the novel use of decaying step-sizes on both gradient and ascent direction in our VMM to significantly improve its learning. We show that our proposed methods is compatible with ResNet features when applied to large class number datasets such as MIT67 and SUN397. Finally, we compare our proposed learner with several recent works such as deep clustering algorithms and showed we were able to produce on par or outperform the state-of-the-art methods in terms of clustering measures.
Deep clustering is an emerging topic in deep learning where traditional clustering is performed in deep learning feature space. However, clustering and deep learning are often mutually exclusive. In the autoencoder based deep clustering, the challenge is how to jointly optimize both clustering and dimension reduction together, so that the weights in the hidden layers are not only guided by reconstruction loss, but also by a loss function associated with clustering. The current state-of-the-art has two fundamental flaws. First, they rely on the mathematical convenience of Kullback-Leibler divergence for the clustering loss function but the former is asymmetric. Secondly, they assume the prior knowledge on the number of clusters is always available for their dataset of interest. This paper tries to improve on these problems. In the first problem, we use a Jensen-Shannon divergence to overcome the asymmetric issue, specifically using a closed form variant. Next, we introduce an infinite cluster representation using Dirichlet process Gaussian mixture model for joint clustering and model selection in the latent space which we called deep model selection. The number of clusters in the latent space are not fixed but instead vary accordingly as they gradually approach the optimal number during training. Thus, prior knowledge is not required. We evaluate our proposed deep model selection method with traditional model selection on large class number datasets such as MIT67 and CIFAR100 and also compare with both traditional variational Bayes model and deep clustering method with convincing results.
Deep clustering is a recent deep learning technique which combines deep learning with traditional unsupervised clustering. At the heart of deep clustering is a loss function which penalizes samples for being an outlier from their ground truth cluster centers in the latent space. The probabilistic variant of deep clustering reformulates the loss using KL divergence. Often, the main constraint of deep clustering is the necessity of a closed form loss function to make backpropagation tractable. Inspired by deep clustering and adversarial net, we reformulate deep clustering as an adversarial net over traditional closed form KL divergence. Training deep clustering becomes a task of minimizing the encoder and maximizing the discriminator. At optimality, this method theoretically approaches the JS divergence between the distribution assumption of the encoder and the discriminator. We demonstrated the performance of our proposed method on several well cited datasets such as SVHN, USPS, MNIST and CIFAR10, achieving on-par or better performance with some of the state-of-the-art deep clustering methods.
This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier .
The availability of highly accurate urban airborne laser scanning (ALS) data will increase rapidly in the future, especially as acquisition costs decrease, for example through the use of drones. Current challenges in data processing are related to the limited spectral information and low point density of most ALS datasets. Another challenge will be the growing need for annotated training data, frequently produced by manual processes, to enable semantic interpretation of point clouds. This study proposes to semantically segment new high-density (1200 points per square metre on average) multispectral ALS data with an unsupervised ground-aware deep clustering method GroupSP inspired by the unsupervised GrowSP algorithm. GroupSP divides the scene into superpoints as a preprocessing step. The neural network is trained iteratively by grouping the superpoints and using the grouping assignments as pseudo-labels. The predictions for the unseen data are given by over-segmenting the test set and mapping the predicted classes into ground truth classes manually or with automated majority voting. GroupSP obtained an overall accuracy (oAcc) of 97% and a mean intersection over union (mIoU) of 80%. When compared to other unsupervised semantic segmentation methods, GroupSP outperformed GrowSP and non-deep K-means. However, a supervised random forest classifier outperformed GroupSP. The labelling efforts in GroupSP can be minimal; it was shown, that the GroupSP can semantically segment seven urban classes (building, high vegetation, low vegetation, asphalt, rock, football field, and gravel) with oAcc of 95% and mIoU of 75% using only 0.004% of the available annotated points in the mapping assignment. Finally, the multispectral information was examined; adding each new spectral channel improved the mIoU. Additionally, echo deviation was valuable, especially when distinguishing ground-level classes.