Abdelmalik Moujahid

Modern computer vision is increasingly driven by the search for representations that generalize across tasks, modalities, and learning settings, rather than excelling at a single benchmark. This has produced a broad collection of architectures and paradigms, including convolutional neural networks (CNNs), Vision Transformers (ViTs), state-space models, foundation models, and diffusion-based generative models. Despite differing in design and training objectives, these approaches increasingly draw on a common set of principles: representation learning, self-attention, self-supervision, multimodal alignment, and generative modeling. As a result, the boundaries between discriminative, multimodal, and generative paradigms are becoming progressively less distinct. This survey examines that convergence through the lens of representation learning. We introduce a formal framework that classifies architectures by which component of an encoder–decoder pipeline they modify, unifies diverse training objectives as instances of a single alignment functional, and formalizes the locality–globality trade-off through two provable relationships linking a model’s locality, its computational cost, and the depth required to reach a global receptive field. Using this framework, we trace the evolution of vision architectures, from convolutional networks and Vision Transformers through hybrid and state-space designs to multimodal foundation models and modern generative frameworks, critically examining the limitations of each paradigm rather than reporting only their successes and complementing this analysis with a quantitative comparison across representative architectures. We show how discriminative, multimodal, and generative learning are converging around shared representational principles, argue for a unified representation-learning perspective on modern computer vision, and outline open challenges and concrete future directions toward general-purpose visual intelligence, multimodal foundation models, and trustworthy deployment.

Time delays are a fundamental feature in modeling stochastic epidemic systems, as they capture the incubation period and other physiological lags inherent in disease transmission. In this work, we investigate a stochastic SIRC (Susceptible-Infectious-Recovered-Cross-immune) epidemic model where the delay is incorporated into the transmission term to reflect the incubation period. To account for environmental variability, we examine two stochastic formulations: the classical approach, which adds independent white noise to each compartment, and a probabilistic, event-driven model in which stochasticity arises directly from transition probabilities.

Machine learning techniques face numerous challenges to achieve optimal performance. These include computational constraints, the limitations of single-view learning algorithms and the complexity of processing large datasets from different domains, sources or views. In this context, multi-view clustering (MVC), a class of unsupervised multi-view learning, emerges as a powerful approach to overcome these challenges. MVC compensates for the shortcomings of single-view methods and provides a richer data representation and effective solutions for a variety of unsupervised learning tasks. In contrast to traditional single-view approaches, the semantically rich nature of multi-view data increases its practical utility despite its inherent complexity. This survey makes a threefold contribution: (1) a systematic categorization of multi-view clustering methods into well-defined groups, including co-training, co-regularization, subspace, deep learning, kernel-based, anchor-based, and graph-based strategies; (2) an in-depth analysis of their respective strengths, weaknesses, and practical challenges, such as scalability and incomplete data; and (3) a forward-looking discussion of emerging trends, interdisciplinary applications, and future directions in MVC research. This study represents an extensive workload, encompassing the review of over 140 foundational and recent publications, the development of comparative insights on integration strategies such as early fusion, late fusion, and joint learning, and the structured investigation of practical use cases in the areas of healthcare, multimedia, and social network analysis. By integrating these efforts, this work aims to fill existing gaps in MVC research and provide actionable insights for the advancement of the field.

Machine learning techniques face numerous challenges to achieve optimal performance. These include computational constraints, the limitations of single-view learning algorithms and the complexity of processing large datasets from different domains, sources or views. In this context, multi-view clustering (MVC), a class of unsupervised multi-view learning, emerges as a powerful approach to overcome these challenges. MVC compensates for the shortcomings of single-view methods and provides a richer data representation and effective solutions for a variety of unsupervised learning tasks. In contrast to traditional single-view approaches, the semantically rich nature of multi-view data increases its practical utility despite its inherent complexity. This survey makes a threefold contribution: (1) a systematic categorization of multi-view clustering methods into well-defined groups, including co-training, co-regularization, subspace, deep learning, kernel-based, anchor-based, and graph-based strategies; (2) an in-depth analysis of their respective strengths, weaknesses, and practical challenges, such as scalability and incomplete data; and (3) a forward-looking discussion of emerging trends, interdisciplinary applications, and future directions in MVC research. This study represents an extensive workload, encompassing the review of over 140 foundational and recent publications, the development of comparative insights on integration strategies such as early fusion, late fusion, and joint learning, and the structured investigation of practical use cases in the areas of healthcare, multimedia, and social network analysis. By integrating these efforts, this work aims to fill existing gaps in MVC research and provide actionable insights for the advancement of the field.

Breast cancer claims thousands of lives annually, emphasizing the need for swift and accurate histopathology image classification to expedite diagnoses. Despite the rapid evolution of Convolutional Neural Networks (CNNs), the conventional softmax loss lacks the robustness required to discern intricate features in breast cancer classification from histopathological images. In response, our study introduces the Cosine Additive Angular Margin Loss (CAAM) to address this limitation and achieve both enhanced intra-class cohesion and distinct inter-class boundaries concurrently. By normalizing weight and feature vectors, we eliminate radial variations before imposing angular and cosine margin constraints on the softmax angle space. This process maximizes the decision margin, resulting in a discriminative feature embedding. Extensive experiments conducted on the BreakHis dataset demonstrate that CAAM consistently outperforms existing methods in breast cancer histopathological image classification. Our findings underscore the efficacy of angular margin-based softmax losses in bolstering the performance of advanced CNN models for breast cancer classification.

When many histopathological breast images with different magnification levels need to be analyzed, diagnosing benign or malignant cancer from the images can be time-consuming. Automatic classification of histopathological images of breast cancer can support the diagnostic workflow in pathology, reducing analysis time. Recently, convolutional neural networks (CNNs) have been used for more accurate classification of breast cancer histopathological images. CNNs typically highlight semantic information to extract discriminative features. However, the traditional softmax loss used by CNNs usually lacks sufficient discriminative power. To address this problem, several angular margin-based softmax loss functions have been proposed, including Large Margin Softmax Loss (A-Softmax), Large Margin Cosine Loss (CosFace), Additive Angular Margin Loss (ArcFace), and Linear ArcFace (Li-ArcFace). All of these improved losses are based on the same concept: maximizing inter-class variance while minimizing intra-class distance. This paper focuses on these four losses and their effectiveness in extracting discriminative features and creating decision margins between classes. Extensive experimental evaluations were conducted on a public and well-known histopathological breast cancer image dataset (BreakHis). Further experiments with the BACH dataset for breast cancer classification and the SARS-CoV-2 CT-scan dataset for COVID-19 detection affirm the generalization capability of angular margin-based softmax losses in medical image classification.