Search

Deep clustering has gained prominence due to its impressive capability to handle high-dimensional real-world data. However, in the absence of ground-truth labels, existing clustering methods struggle to discern false positives that resemble the target cluster and false negatives that visually differ but maintain semantic consistency. The unreliable projections caused by visual ambiguity disrupt representation learning, leading to sub-optimal clustering outcomes. To address this challenge, we propose a novel method called uncertainty-based learning for deep clustering (ULDC), which aims to discover more optimal cluster structures within data from an uncertainty perspective. Specifically, we utilize the Dirichlet distribution to quantify the uncertainty of feature projections in the latent space, providing a probabilistic framework for modeling uncertainty during the clustering process. We then develop uncertainty-based learning to mitigate the interference caused by false positives and negatives in the clustering tasks. Additionally, a semantic calibration module is introduced to achieve a global alignment of cross-instance semantics, facilitating the learning of clustering-favorite representations. Extensive experiments on five widely-used benchmarks demonstrate the effectiveness of ULDC. The source code is available from . [ABSTRACT FROM AUTHOR]

Background: Single-cell RNA sequencing (scRNA-seq) has transformed biological research by offering new insights into cellular heterogeneity, developmental processes, and disease mechanisms. As scRNA-seq technology advances, its role in modern biology has become increasingly vital. This study explores the application of deep learning to single-cell data clustering, with a particular focus on managing sparse, high-dimensional data. Results: We propose the SMD deep learning model, which integrates nonlinear dimensionality reduction techniques with a porous dilated attention gate component. Built upon a convolutional autoencoder and informed by the negative binomial distribution, the SMD model efficiently captures essential cell clustering features and dynamically adjusts feature weights. Comprehensive evaluation on both public datasets and proprietary osteosarcoma data highlights the SMD model's efficacy in achieving precise classifications for single-cell data clustering, showcasing its potential for advanced transcriptomic analysis. Conclusion: This study underscores the potential of deep learning-specifically the SMD model-in advancing single-cell RNA sequencing data analysis. By integrating innovative computational techniques, the SMD model provides a powerful framework for unraveling cellular complexities, enhancing our understanding of biological processes, and elucidating disease mechanisms. The code is available from https://github.com/xiaoxuc/scSMD. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in deep learning-based clustering. A recently introduced technique called DipDECK has shown effective performance on large and high-dimensional datasets. DipDECK utilises Hartigan's dip test, a statistical test, to merge small non-viable clusters. Notably, DipDECK was the first deep learning-based clustering technique to incorporate the dip test. However, the number of initial clusters of DipDECK is overestimated and the algorithm then randomly selects the initial seeds to produce the final clusters for a dataset. Therefore, in this paper, we presented a technique called UNSDipDECK , which is an improved version of DipDECK and does not require user input for datasets with an unknown number of clusters. UNSDipDECK produces high-quality initial seeds and the initial number of clusters through a deterministic process. UNSDipDECK uses the unique closest neighbourhood and unique neighbourhood set approaches to determine high-quality initial seeds for a dataset. In our study, we compared the performance of UNSDipDECK with fifteen baseline clustering techniques, including DipDECK, using NMI and ARI metrics. The experimental results indicate that UNSDipDECK outperforms the baseline techniques, including DipDECK. Additionally, we demonstrated that the initial seed selection process significantly contributes to UNSDipDECK 's ability to produce high-quality clusters. [ABSTRACT FROM AUTHOR]

Rehabilitation of gait function in post-stroke hemiplegic patients is critical for improving mobility and quality of life, requiring a comprehensive understanding of individual gait patterns. Previous studies on gait analysis using unsupervised clustering often involve manual feature extraction, which introduces limitations such as low accuracy, low consistency, and potential bias due to human intervention. This cross-sectional study aimed to identify and cluster gait patterns using an end-to-end deep learning approach that autonomously extracts features from joint angle trajectories for a gait cycle, minimizing human intervention. A total of 74 sub-acute post-stroke hemiplegic patients with lower limb impairments were included in the analysis. The dataset comprised 219 sagittal plane joint angle and angular velocity trajectories from the hip, knee, and ankle joints during gait cycles. Deep temporal clustering was employed to cluster them in an end-to-end manner by simultaneously optimizing feature extraction and clustering, with hyperparameter tuning tailored for kinematic gait cycle data. Through this method, six optimal clusters were selected with a silhouette score of 0.2831, which is a relatively higher value compared to other clustering algorithms. To clarify the characteristics of the selected groups, in-depth statistics of spatiotemporal, kinematic, and clinical features are presented in the results. The results demonstrate the effectiveness of end-to-end deep learning-based clustering, yielding significant performance improvements without the need for manual feature extraction. While this study primarily utilizes sagittal plane data, future analysis incorporating coronal and transverse planes as well as muscle activity and gait symmetry could provide a more comprehensive understanding of gait patterns. [ABSTRACT FROM AUTHOR]

Existing deep fuzzy clustering methods employ deep neural networks to extract high-level feature embeddings from data, thereby enhancing subsequent clustering and achieving superior performance compared to traditional methods. However, solely relying on feature embeddings may cause clustering models to ignore detailed information within data. To address this issue, this paper designs a deep multi-semantic fuzzy K-means (DMFKM) model. Our method harnesses the semantic complementarity of various kinds of features within autoencoder to improve clustering performance. Additionally, to fully exploit the contribution of different types of features to each cluster, we propose an adaptive weight adjustment mechanism to dynamically calculate the importance of different features during clustering. To validate the effectiveness of the proposed method, we applied it to six benchmark datasets. DMFKM significantly outperforms the prevailing fuzzy clustering techniques across different evaluation metrics. Specifically, on the six benchmark datasets, our method achieves notable gains over the second-best comparison method, with an ACC improvement of approximately 2.42%, a Purity boost of around 1.94%, and an NMI enhancement of roughly 0.65%. [ABSTRACT FROM AUTHOR]

The introduction of GPS technology has led to the creation of vast amounts of spatio-temporal data, which captures the movement patterns of different things. Efficient allocation of resources to ensure user satisfaction is a crucial factor in shaping the future of urban planning and development. It is required to comprehend the factors that can contribute to the creation of methods for studying user behaviours using a substantial number of persons within a brief timeframe. It is essential to employ appropriate clustering approaches to analyze this data in order to comprehend spatio-temporal behaviours.Heatmaps offer a graphical display of changes in density across both location and Time, making them a user-friendly tool for initial data analysis and identifying areas of high activity. The Spatio-Temporal Dynamic Graph Neural Network (ST-DGNN) utilizes graph neural networks to represent the intricate connections present in spatio-temporal data, encompassing both spatial interdependencies and temporal changes. Our methodology improves the accuracy and interpretability of trajectory clustering by integrating different methods. The suggested method has been shown to identify relevant clusters effectively and reveal noteworthy spatio-temporal characteristics through experimental analysis on real-world GPS datasets. The research utilizes a dataset comprising 182 users for analysis. Numerous measures are taken to boost the clustering accuracy of the applied techniques, including addressing missing values and outliers. Additionally, this thesis introduces a framework for time estimation based on graph-based deep learning, termed Spatio-Temporal Dual Graph Neural II Networks (STDGNN). The method entails constructing node-level and edge-level graphs that depict the adjacency connections between intersections and road segments. The results showed a number of cluster changes in each period of time dependent on move users and period; for example, the (2592) cluster of period one hour.

Multi-view clustering aims to explore the feature information of objects from multiple perspectives to obtain accurate clustering results. However, existing research often fails to handle the information conflicts that arise during view fusion and does not fully utilize the complementary information between multiple views. To address these issues, this paper proposed a self-supervised multi-view clustering model guided by multi-angle semantic labels. The model first mapped the latent representations of each view to independent low-dimensional feature spaces, focusing on optimizing the consistency between views in one space to maintain the local structure of the feature space and the relative relationships between samples. At the same time, in another space, clustering information was directly extracted from the view level to capture richer and more diverse semantic features. Finally, pseudo-labels generated from multi-angle semantic features guided the clustering assignment at the object level, achieving collaborative optimization of the two representations. Extensive experimental results demonstrate that this approach can comprehensively explore both common and complementary information in multi-view data and exhibit good clustering performance. Moreover, compared to other methods, this approach has advantages in scenarios with a larger number of views. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ordnance Equipment Engineering is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Unsupervised semantic segmentation (USS) aims at partitioning an image into semantically meaningful segments by learning from a collection of unlabeled images. The effectiveness of current approaches is plagued by difficulties in coordinating representation learning and pixel clustering, modeling the varying feature distributions of different classes, handling outliers and noise, and addressing the pixel class imbalance problem. This paper introduces a novel approach, termed Imbalance-Aware Dense Discriminative Clustering (IDDC), for USS, which addresses all these difficulties in a unified framework. Different from existing approaches, which learn USS in two stages (i.e., generating and updating pseudo masks, or refining and clustering embeddings), IDDC learns pixel-wise feature representation and dense discriminative clustering in an end-to-end and self-supervised manner, through a novel objective function that transfers the manifold structure of pixels in the embedding space of a vision Transformer (ViT) to the label space while tolerating the noise in pixel affinities. During inference, the trained model directly outputs the classification probability of each pixel conditioned on the image. In addition, this paper proposes a new regularizer, based on the Weibull function, to handle pixel class imbalance and cluster degeneration in a single shot. Experimental results demonstrate that IDDC significantly outperforms all previous USS methods on three real-world datasets, COCO-Stuff-27, COCO-Stuff-171, and Cityscapes. Extensive ablation studies validate the effectiveness of each design. Our code is available at https://github.com/MY-LIU100101/IDDC. [ABSTRACT FROM AUTHOR]

The application of contrastive learning in image clustering in the field of unsupervised learning has attracted much attention due to its ability to effectively improve clustering performance. Extracting features for face-oriented clustering using deep learning networks has also become one of the key challenges in this field. Some current research focuses on learning valuable semantic features using contrastive learning strategies to accomplish cluster allocation in the feature space. However, some studies decoupled the two phases of feature extraction and clustering are prone to error transfer, on the other hand, features learned in the feature extraction phase of multi-stage training are not guaranteed to be suitable for the clustering task. To address these challenges, We propose an end-to-end multi-branch feature fusion comparison deep clustering method (SwEAC), which incorporates a multi-branch feature extraction strategy in the representation learning phase, this method completes the clustering center comparison between multiple views and then assigns clusters to the extracted features. In order to extract higher-level semantic features, a multi-branch structure is used to learn multi-dimensional spatial channel dimension information and weighted receptive-field spatial features, achieving cross-dimensional information exchange of multi-branch sub-features. Meanwhile, we jointly optimize unsupervised contrastive representation learning and clustering in an end-to-end architecture to obtain semantic features for clustering that are more suitable for clustering tasks. Experimental results show that our model achieves good clustering performance on three popular image datasets evaluated by three unsupervised evaluation metrics, which proves the effectiveness of end-to-end multi-branch feature fusion comparison deep clustering methods. [ABSTRACT FROM AUTHOR]

BackgroundPhysiological motion, such as respiratory motion, has become a limiting factor in the spatial resolution of positron emission tomography (PET) imaging as the resolution of PET detectors continue to improve. Motion-induced misregistration between PET and CT images can also cause attenuation correction artifacts. Respiratory gating can be used to freeze the motion and to reduce motion induced artifacts.PurposeIn this study, we propose a robust data-driven approach using an unsupervised deep clustering network that employs an autoencoder (AE) to extract latent features for respiratory gating.MethodsWe first divide list-mode PET data into short-time frames. The short-time frame images are reconstructed without attenuation, scatter, or randoms correction to avoid attenuation mismatch artifacts and to reduce image reconstruction time. The deep AE is then trained using reconstructed short-time frame images to extract latent features for respiratory gating. No additional data are required for the AE training. K-means clustering is subsequently used to perform respiratory gating based on the latent features extracted by the deep AE. The effectiveness of our proposed Deep Clustering method was evaluated using physical phantom and real patient datasets. The performance was compared against phase gating based on an external signal (External) and image based principal component analysis (PCA) with K-means clustering (Image PCA).ResultsThe proposed method produced gated images with higher contrast and sharper myocardium boundaries than those obtained using the External gating method and Image PCA. Quantitatively, the gated images generated by the proposed Deep Clustering method showed larger center of mass (COM) displacement and higher lesion contrast than those obtained using the other two methods.ConclusionsThe effectiveness of our proposed method was validated using physical phantom and real patient data. The results showed our proposed framework could provide superior gating than the conventional External method and Image PCA.

This paper proposes an intelligent sensing framework for Internet-of-Things platforms, where sensor measurements stem from multiple causes. Sensors are selectively chosen for data collection to identify the cause with partial measurements. We employ variational deep embedding, a generative model capable of clustering and generation, to identify causes, cluster measurements accordingly, and determine causes for estimating complete measurements from partial data. These estimates aid in efficient sensor selection for data collection. Results demonstrate early and reliable cause sensing and complete measurement estimation using the proposed framework.

Abstract Single-cell ribonucleic acid sequencing (scRNA-seq) is a high-throughput genomic technique that is utilized to investigate single-cell transcriptomes. Cluster analysis can effectively reveal the heterogeneity and diversity of cells in scRNA-seq data, but existing clustering algorithms struggle with the inherent high dimensionality, noise, and sparsity of scRNA-seq data. To overcome these limitations, we propose a clustering algorithm: the Dual Correlation Reduction network-based Extreme Learning Machine (DCRELM). First, DCRELM obtains the low-dimensional and dense result features of scRNA-seq data in an extreme learning machine (ELM) random mapping space. Second, the ELM graph distortion module is employed to obtain a dual view of the resulting features, effectively enhancing their robustness. Third, the autoencoder fusion module is employed to learn the attributes and structural information of the resulting features, and merge these two types of information to generate consistent latent representations of these features. Fourth, the dual information reduction network is used to filter the redundant information and noise in the dual consistent latent representations. Last, a triplet self-supervised learning mechanism is utilized to further improve the clustering performance. Extensive experiments show that the DCRELM performs well in terms of clustering performance and robustness. The code is available at https://github.com/gaoqingyun-lucky/awesome-DCRELM .

Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the original graph structure will suffer from sparsity problems, and will also result in suboptimal node clustering performance. In this paper, we propose a hypergraph network embedding (HGNE) for community detection to solve the above problems. Firstly, we construct potential connections based on the shared feature information of the nodes. By fusing the original topology with feature-based potential connections, both the explicit and implicit relationships are encoded into the node representations, thus alleviating the sparsity problem. Secondly, for integrating the higher-order relationship, we adopt hypergraph convolution to encode the higher-order correlations. To constrain the quality of the node embedding, the spectral hypergraph embedding loss is utilized. Furthermore, we design a dual-contrast mechanism, which draws similar nodes closer by comparing the representations of different views. This mechanism can efficiently prevent multi-node classes from distorting less-node classes. Finally, the dual-contrast mechanism is jointly optimized with self-training clustering to obtain more robust node representations, thus improving the clustering results. Extensive experiments on five datasets indicate the superiority and effectiveness of HGNE. [ABSTRACT FROM AUTHOR]

Potential inconsistencies between the goals of unsupervised representation learning and clustering within multi-stage deep clustering can diminish the effectiveness of these techniques. However, because the goal of unsupervised representation learning is inherently flexible and can be tailored to clustering, we introduce PointStaClu, a novel single-stage point cloud clustering method. This method employs stable cluster discrimination (StaClu) to tackle the inherent instability present in single-stage deep clustering training. It achieves this by constraining the gradient descent updates for negative instances within the cross-entropy loss function, and by updating the cluster centers using the same loss function. Furthermore, we integrate entropy constraints to regulate the distribution entropy of the dataset, thereby enhancing the cluster allocation. Our framework simplifies the process, employing a single loss function and an encoder for deep point cloud clustering. Extensive experiments on the ModelNet40 and ShapeNet dataset demonstrate that PointStaClu significantly narrows the performance gap between unsupervised point cloud clustering and supervised point cloud classification, presenting a novel approach to point cloud classification tasks. [ABSTRACT FROM AUTHOR]

In this study, a novel hybrid deep clustering approach is proposed for the effective moving object segmentation. Initially, the data is collected, and the keyframe selection is performed using the threshold-based Kennard–Stone method. Then, the preprocessing step involves noise filtering using bilateral wavelet thresholding and binary color conversion. The blob detection is performed using normalized Laplacian of Gaussian. Finally, the segmentation of moving objects is performed using a hybrid clustering approach called improved fuzzy C-mean (IFCM) clustering with chaotic salp swarm (CSS) optimization algorithm (Hybrid IFCM-CSS). The overall evaluation is done in MATLAB. The performance of the hybrid IFCM-CSS is compared to other approaches based on some measures. The proposed Hybrid IFCM-CSS achieves the highest precision of 0.971, using the SBM-RGBD dataset. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding factor that disturbs the cluster analysis. Existing methods eliminate the biases by projecting data onto the orthogonal complement of the subspace expanded by the confounding factor before clustering. Therein, the interested clustering factor and the confounding factor are coarsely considered in the raw feature space, where the correlation between the data and the confounding factor is ideally assumed to be linear for convenient solutions. These approaches are thus limited in scope as the data in real applications is usually complex and non-linearly correlated with the confounding factor. This paper presents a new clustering framework named Sanitized Clustering Against confounding Bias, which removes the confounding factor in the semantic latent space of complex data through a non-linear dependence measure. To be specific, we eliminate the bias information in the latent space by minimizing the mutual information between the confounding factor and the latent representation delivered by variational auto-encoder. Meanwhile, a clustering module is introduced to cluster over the purified latent representations. Extensive experiments on complex datasets demonstrate that our SCAB achieves a significant gain in clustering performance by removing the confounding bias. [ABSTRACT FROM AUTHOR]

The aim of this study was address the challenges posed by the manual labeling of fetal ultrasound images by introducing an unsupervised approach, the fetal ultrasound semantic clustering (FUSC) method. The primary objective was to automatically cluster a large volume of ultrasound images into various fetal views, reducing or eliminating the need for labor-intensive manual labeling. The FUSC method was developed by using a substantial data set comprising 88,063 images. The methodology involves an unsupervised clustering approach to categorize ultrasound images into diverse fetal views. The method's effectiveness was further evaluated on an additional, unseen data set consisting of 8187 images. The evaluation included assessment of the clustering purity, and the entire process is detailed to provide insights into the method's performance. The FUSC method exhibited notable success, achieving >92% clustering purity on the evaluation data set of 8187 images. The results signify the feasibility of automatically clustering fetal ultrasound images without relying on manual labeling. The study showcases the potential of this approach in handling a large volume of ultrasound scans encountered in clinical practice, with implications for improving efficiency and accuracy in fetal ultrasound imaging. The findings of this investigation suggest that the FUSC method holds significant promise for the field of fetal ultrasound imaging. By automating the clustering of ultrasound images, this approach has the potential to reduce the manual labeling burden, making the process more efficient. The results pave the way for advanced automated labeling solutions, contributing to the enhancement of clinical practices in fetal ultrasound imaging. Our code is available at https://github.com/BioMedIA-MBZUAI/FUSC. [ABSTRACT FROM AUTHOR]

Deep clustering is an approach that uses deep learning to cluster data, since it involves training a neural network model to become familiar with a data representation that is suitable for clustering. Deep clustering has been applied to a wide range of data types, including images, texts, time series and has the advantage of being able to automatically learn features from the data, which can be more effective than using hand-crafted features. It is also able to handle high-dimensional data, such as time series with many variables, which can be challenging for traditional clustering techniques. In this paper, we introduce a novel deep neural network type to improve the performance of the auto-encoder part by ignoring the unnecessary extra-noises and labelling the input data. Our approach is helpful when just a limited amount of labelled data is available, but labelling a big amount of data would be costly or time-consuming. It also applies for the data in high-dimensional and difficult to define a good set of features for clustering. [ABSTRACT FROM AUTHOR]

Deep spectral clustering techniques are considered one of the most efficient clustering algorithms in data mining field. The similarity between instances and the disparity among classes are two critical factors in clustering fields. However, most current deep spectral clustering approaches do not sufficiently take them both into consideration. To tackle the above issue, we propose Semantic Spectral clustering with Contrastive learning and Neighbor mining (SSCN) framework, which performs instance-level pulling and cluster-level pushing cooperatively. Specifically, we obtain the semantic feature embedding using an unsupervised contrastive learning model. Next, we obtain the nearest neighbors partially and globally, and the neighbors along with data augmentation information enhance their effectiveness collaboratively on the instance level as well as the cluster level. The spectral constraint is applied by orthogonal layers to satisfy conventional spectral clustering. Extensive experiments demonstrate the superiority of our proposed frame of spectral clustering. [ABSTRACT FROM AUTHOR]

Audio data augmentation is widely adopted in automatic speech recognition (ASR) to alleviate the overfitting problem. However, noise-based data augmentation converts an over-fitting problem into an under-fitting problem which increases the training time severely. With noise-based data augmentation, informative features are not be persisted during the generating process and generated audio clips would become noise data for the acoustic model. To face the challenge, we propose an Adaptive audio Data Augmentation method called ADA with deep clustering. The proposed ADA could automatically select the most informative augmented sample for each generation. Moreover, two sample selection strategies called RM and RS are proposed. The proposed RM removes samples whose embedding are far away from the cluster center, while the proposed RS maintains the diversity of augmentation samples by sampling in each cluster. Experiments on Aishell-1 demonstrate that the proposed ADA method could improve the data efficiency of end-to-end ASR model in both CNN-based and Transformer-based networks. The proposed ADA obtains an 11.28% and 5.95% relative improvement on SS-CNN and LS-CNN, and a 4.35% improvement on S-Transformer compared with the state-of-the-art audio data augmentation method. Meanwhile, the proposed ADA method decreases the demand of augmented samples by 2.7 times in SS-CNN, LS-CNN and S-Transformer. The qualitative and quantitative analysis proves the effectiveness and efficiency of the proposed ADA method. [ABSTRACT FROM AUTHOR]

White blood cells (WBCs) are cells of the immune system that protect the body from infectious diseases and invading bacteria and viruses. An accurate assessment of their quantity is considered of utmost importance in its initial stage for evaluating a probable disease. Because of the aberrant number of WBV, both abnormal increase and decline indicate infective disease seriousness. Several methods were devised for WBC segmentation; issues like over segmentation problems, poor contrast, and improper detection of seed points affect the performance. Therefore, this work aims to develop an automatic deep clustering based segmentation with cell size determination for accurate diagnosis as well as treatment planning. The steps followed for processing the image segmentation based on the deep clustering model are Image Pre-processing, Deep Clustering based Segmentation, Cell size Determination and Classification. Initially, pre-processing images is necessary to enhance the quality of the raw input images. Next, in WBCs (White Blood Cells), accurate segmentation remains a critical task due to variations in cell types, changes in staining techniques, colour, and shape. Here, an automated Deep U-Net with clustering based segmentation (Deep U_ClusterNet) is presented to achieve semantic multi-label segmentation using U-network along with deep clustering based on Spatial Reliable FCM (Fuzzy C-Means) Clustering model. The proposed Deep U_ClusterNet achieved better performance in terms of Accuracy, Recall, Specificity, Precision, and Dice similarity coefficient (DSC) and acquired the maximal values of 0.982, 0.998, 0.983, 0.957, and 0.951, respectively. [ABSTRACT FROM AUTHOR]

Multi-view clustering has attracted growing attention owing to its powerful capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally fail to distinguish the unequal importance of multiple views to the clustering task and overlook the scale uniformity of learned latent representation among different views, resulting in blurry physical meaning and suboptimal model performance. To address these issues, in this paper, we propose a joint learning framework, termed Adaptive-weighted deep Multi-view Clustering with Uniform scale representation (AMCU). Specifically, to achieve more reasonable multi-view fusion, we introduce an adaptive weighting strategy, which imposes simplex constraints on heterogeneous views for measuring their varying degrees of contribution to consensus prediction. Such a simple yet effective strategy shows its clear physical meaning for the multi-view clustering task. Furthermore, a novel regularizer is incorporated to learn multiple latent representations sharing approximately the same scale, so that the objective for calculating clustering loss cannot be sensitive to the views and thus the entire model training process can be guaranteed to be more stable as well. Through comprehensive experiments on eight popular real-world datasets, we demonstrate that our proposal performs better than several state-of-the-art single-view and multi-view competitors. [ABSTRACT FROM AUTHOR]

Deep learning has been recently used to extract the relevant features for representing input data also in the unsupervised setting. However, state-of-the-art techniques focus mostly on algorithmic efficiency and accuracy rather than mimicking the input manifold. On the contrary, competitive learning is a powerful tool for replicating the input distribution topology. It is cognitive/biologically inspired as it is founded on Hebbian learning, a neuropsychological theory claiming that neurons can increase their specialization by competing for the right to respond to/represent a subset of the input data. This paper introduces a novel perspective by combining these two techniques: unsupervised gradient-based and competitive learning. The theory is based on the intuition that neural networks can learn topological structures by working directly on the transpose of the input matrix. At this purpose, the vanilla competitive layer and its dual are presented. The former is representative of a standard competitive layer for deep clustering, while the latter is trained on the transposed matrix. The equivalence of the layers is extensively proven both theoretically and experimentally. The dual competitive layer has better properties. Unlike the vanilla layer, it directly outputs the prototypes of the data inputs, while still allowing learning by backpropagation. More importantly, this paper proves theoretically that the dual layer is better suited for handling high-dimensional data (e.g., for biological applications), because the estimation of the weights is driven by a constraining subspace which does not depend on the input dimensionality, but only on the dataset cardinality. This paper has introduced a novel approach for unsupervised gradient-based competitive learning. This approach is very promising both in the case of small datasets of high-dimensional data and for better exploiting the advantages of a deep architecture: the dual layer perfectly integrates with the deep layers. A theoretical justification is also given by using the analysis of the gradient flow for both vanilla and dual layers. [ABSTRACT FROM AUTHOR]

The appropriate understanding and fast processing of lengthy legal documents are computationally challenging problems. Designing efficient automatic summarization techniques can potentially be the key to deal with such issues. Extractive summarization is one of the most popular approaches for forming summaries out of such lengthy documents, via the process of summary-relevant sentence selection. An efficient application of this approach involves appropriate scoring of sentences, which helps in the identification of more informative and essential sentences from the document. In this work, a novel sentence scoring approach DCESumm is proposed which consists of supervised sentence-level summary relevance prediction, as well as unsupervised clustering-based document-level score enhancement. Experimental results on two legal document summarization datasets, BillSum and Forum of Information Retrieval Evaluation (FIRE), reveal that the proposed approach can achieve significant improvements over the current state-of-the-art approaches. More specifically it achieves ROUGE metric F1-score improvements of (1−6)% and (6−12)% for the BillSum and FIRE test sets respectively. Such impressive summarization results suggest the usefulness of the proposed approach in finding the gist of a lengthy legal document, thereby providing crucial assistance to legal practitioners. [ABSTRACT FROM AUTHOR]

By cooperatively learning features and assigning clusters, deep clustering is superior to conventional clustering algorithms. Numerous deep clustering algorithms have been developed for a variety of application levels; however, the majority are still incapable of learning robust noise-resistant latent features, which limits the clustering performance. To address this open research challenge, we introduce, for the first time, a new approach called: Robust Deep Embedded Image Clustering algorithm with Separable Krawtchouk and Hahn Moments (RDEICSKHM). Our approach leverages the advantages of Krawtchouk and Hahn moments, such as local feature extraction, discrete orthogonality, and noise tolerance, to obtain a meaningful and robust image representation. Moreover, we employ LayerNormalization to further improve the latent space quality and facilitate the clustering process. We evaluate our approach on four image datasets: MNIST, MNIST-test, USPS, and Fashion-MNIST. We compare our method with several deep clustering methods based on two metrics: clustering accuracy (ACC) and normalized mutual information (NMI). The experimental results show that our method achieves superior or competitive performance on all datasets, demonstrating its effectiveness and robustness for deep image clustering.