Djamel Eddine Boukhari

Fadi Abdeladhim Zidi, Djamel Eddine Boukhari, Abdellah Zakaria Sellam et al.

Hyperspectral image classification remains a challenging task due to the high dimensionality of spectral data, significant inter-band redundancy, and the limited availability of annotated samples. While recent transformer-based models have improved the global modeling of spectral-spatial dependencies, their scalability and adaptability under label-scarce conditions remain limited. In this work, we propose \textbf{LoLA-SpecViT}(Low-rank adaptation Local Attention Spectral Vision Transformer), a lightweight spectral vision transformer that addresses these limitations through a parameter-efficient architecture tailored to the unique characteristics of hyperspectral imagery. Our model combines a 3D convolutional spectral front-end with local window-based self-attention, enhancing both spectral feature extraction and spatial consistency while reducing computational complexity. To further improve adaptability, we integrate low-rank adaptation (LoRA) into attention and projection layers, enabling fine-tuning with over 80\% fewer trainable parameters. A novel cyclical learning rate scheduler modulates LoRA adaptation strength during training, improving convergence and generalisation. Extensive experiments on three benchmark datasets WHU-Hi LongKou, WHU-Hi HongHu, and Salinas demonstrate that LoLA-SpecViT consistently outperforms state-of-the-art baselines, achieving up to 99.91\% accuracy with substantially fewer parameters and enhanced robustness under low-label regimes. The proposed framework provides a scalable and generalizable solution for real-world HSI applications in agriculture, environmental monitoring, and remote sensing analytics. Our code is available in the following \href{https://github.com/FadiZidiDz/LoLA-SpecViT}{GitHub Repository}.

Djamel Eddine Boukhari

The computational assessment of facial attractiveness, a challenging subjective regression task, is dominated by architectures with a critical trade-off: Convolutional Neural Networks (CNNs) offer efficiency but have limited receptive fields, while Vision Transformers (ViTs) model global context at a quadratic computational cost. To address this, we propose Mamba-CNN, a novel and efficient hybrid architecture. Mamba-CNN integrates a lightweight, Mamba-inspired State Space Model (SSM) gating mechanism into a hierarchical convolutional backbone. This core innovation allows the network to dynamically modulate feature maps and selectively emphasize salient facial features and their long-range spatial relationships, mirroring human holistic perception while maintaining computational efficiency. We conducted extensive experiments on the widely-used SCUT-FBP5500 benchmark, where our model sets a new state-of-the-art. Mamba-CNN achieves a Pearson Correlation (PC) of 0.9187, a Mean Absolute Error (MAE) of 0.2022, and a Root Mean Square Error (RMSE) of 0.2610. Our findings validate the synergistic potential of combining CNNs with selective SSMs and present a powerful new architectural paradigm for nuanced visual understanding tasks.

Djamel Eddine Boukhari

Automated Facial Beauty Prediction (FBP) is a challenging computer vision task due to the complex interplay of local and global facial features that influence human perception. While Convolutional Neural Networks (CNNs) excel at feature extraction, they often process information at a fixed scale, potentially overlooking the critical inter-dependencies between features at different levels of granularity. To address this limitation, we introduce the Scale-Interaction Transformer (SIT), a novel hybrid deep learning architecture that synergizes the feature extraction power of CNNs with the relational modeling capabilities of Transformers. The SIT first employs a multi-scale module with parallel convolutions to capture facial characteristics at varying receptive fields. These multi-scale representations are then framed as a sequence and processed by a Transformer encoder, which explicitly models their interactions and contextual relationships via a self-attention mechanism. We conduct extensive experiments on the widely-used SCUT-FBP5500 benchmark dataset, where the proposed SIT model establishes a new state-of-the-art. It achieves a Pearson Correlation of 0.9187, outperforming previous methods. Our findings demonstrate that explicitly modeling the interplay between multi-scale visual cues is crucial for high-performance FBP. The success of the SIT architecture highlights the potential of hybrid CNN-Transformer models for complex image regression tasks that demand a holistic, context-aware understanding.

Djamel Eddine Boukhari

The automated prediction of facial beauty is a benchmark task in affective computing that requires a sophisticated understanding of both local aesthetic details (e.g., skin texture) and global facial harmony (e.g., symmetry, proportions). Existing models, based on either Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs), exhibit inherent architectural biases that limit their performance; CNNs excel at local feature extraction but struggle with long-range dependencies, while ViTs model global relationships at a significant computational cost. This paper introduces the \textbf{Mamba-Diffusion Network (MD-Net)}, a novel dual-stream architecture that resolves this trade-off by delegating specialized roles to state-of-the-art models. The first stream leverages a frozen U-Net encoder from a pre-trained latent diffusion model, providing a powerful generative prior for fine-grained aesthetic qualities. The second stream employs a Vision Mamba (Vim), a modern state-space model, to efficiently capture global facial structure with linear-time complexity. By synergistically integrating these complementary representations through a cross-attention mechanism, MD-Net creates a holistic and nuanced feature space for prediction. Evaluated on the SCUT-FBP5500 benchmark, MD-Net sets a new state-of-the-art, achieving a Pearson Correlation of \textbf{0.9235} and demonstrating the significant potential of hybrid architectures that fuse generative and sequential modeling paradigms for complex visual assessment tasks.

Djamel Eddine Boukhari

Facial Beauty Prediction (FBP) is a complex and challenging computer vision task, aiming to model the subjective and intricate nature of human aesthetic perception. While deep learning models, particularly Convolutional Neural Networks (CNNs), have made significant strides, they often struggle to capture the global, holistic facial features that are critical to human judgment. Vision Transformers (ViT) address this by effectively modeling long-range spatial relationships, but their quadratic complexity can be a bottleneck. This paper introduces a novel, heterogeneous ensemble architecture, \textbf{VM-BeautyNet}, that synergistically fuses the complementary strengths of a Vision Transformer and a Mamba-based Vision model, a recent advancement in State-Space Models (SSMs). The ViT backbone excels at capturing global facial structure and symmetry, while the Mamba backbone efficiently models long-range dependencies with linear complexity, focusing on sequential features and textures. We evaluate our approach on the benchmark SCUT-FBP5500 dataset. Our proposed VM-BeautyNet achieves state-of-the-art performance, with a \textbf{Pearson Correlation (PC) of 0.9212}, a \textbf{Mean Absolute Error (MAE) of 0.2085}, and a \textbf{Root Mean Square Error (RMSE) of 0.2698}. Furthermore, through Grad-CAM visualizations, we provide interpretability analysis that confirms the complementary feature extraction of the two backbones, offering new insights into the model's decision-making process and presenting a powerful new architectural paradigm for computational aesthetics.