HTHedi Tabia

Hedi Tabia

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hedi Tabia has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Contributions to 3D-shape matching, retrieval and classification

    by Hedi Tabia

    Classification et recherche d’objets 3D: Les solutions existantes pour la recherche et la classification d’objets 3D sont très sensible à la grande variabilité des formes et elles ne sont pas robustes aux transformations affines ou isométriques qu’un objet peut subir. Dans ce contexte, l’objectif de ma recherche est de développer un système qui peut automatiquement retrouver rapidement et avec précision des modèles 3D visuellement similaire à un objet 3D requête. Le système doit être robuste aux transformations non rigides qu’une forme peut subir. Durant ma thèse de doctorat, nous avons développé une nouvelle approche pour la mise en correspondance des objets 3D avec la présence des transformations non-rigides et des modèles partiellement similaires. Nous avons proposé d’utiliser une nouvelle représentation des surfaces 3D à l’aide d’un ensemble de courbes 3D extraites autour des points caractéristiques. Des outils d’analyse de la forme des courbes sont appliqués pour analyser et de comparer les courbes des surfaces 3D. Nous avons utilisé les fonctions de croyance,comme technique de fusion afin de définir une distance globale entre deux objets 3D. Nous avons également expérimenté cette technique dans la recherche et la classification 3D. Nous avons exploré les techniques de sac à mots pour la recherche et la classification des objets 3D.

  • Open Access

    HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks

    by Yanick Chistian Tchenko, Felix Mohr, Hicham Hadj Abdelkader, Hedi Tabia

    A prevailing trend in neural network research suggests that model performance improves with increasing depth and capacity - often at the cost of integrability and efficiency. In this paper, we propose a strategy to optimize small, deployable models by enhancing their capabilities through structured knowledge inheritance. We introduce Hereditary Knowledge Transfer (HKT), a biologically inspired framework for modular and selective transfer of task-relevant features from a larger, pretrained parent network to a smaller child model. Unlike standard knowledge distillation, which enforces uniform imitation of teacher outputs, HKT draws inspiration from biological inheritance mechanisms - such as memory RNA transfer in planarians - to guide a multi-stage process of feature transfer. Neural network blocks are treated as functional carriers, and knowledge is transmitted through three biologically motivated components: Extraction, Transfer, and Mixture (ETM). A novel Genetic Attention (GA) mechanism governs the integration of inherited and native representations, ensuring both alignment and selectivity. We evaluate HKT across diverse vision tasks, including optical flow (Sintel, KITTI), image classification (CIFAR-10), and semantic segmentation (LiTS), demonstrating that it significantly improves child model performance while preserving its compactness. The results show that HKT consistently outperforms conventional distillation approaches, offering a general-purpose, interpretable, and scalable solution for deploying high-performance neural networks in resource-constrained environments.

  • Open Access

    Text-driven Motion Generation: Overview, Challenges and Directions

    by Ali Rida Sahili, Najett Neji, Hedi Tabia

    Text-driven motion generation offers a powerful and intuitive way to create human movements directly from natural language. By removing the need for predefined motion inputs, it provides a flexible and accessible approach to controlling animated characters. This makes it especially useful in areas like virtual reality, gaming, human-computer interaction, and robotics. In this review, we first revisit the traditional perspective on motion synthesis, where models focused on predicting future poses from observed initial sequences, often conditioned on action labels. We then provide a comprehensive and structured survey of modern text-to-motion generation approaches, categorizing them from two complementary perspectives: (i) architectural, dividing methods into VAE-based, diffusion-based, and hybrid models; and (ii) motion representation, distinguishing between discrete and continuous motion generation strategies. In addition, we explore the most widely used datasets, evaluation methods, and recent benchmarks that have shaped progress in this area. With this survey, we aim to capture where the field currently stands, bring attention to its key challenges and limitations, and highlight promising directions for future exploration. We hope this work offers a valuable starting point for researchers and practitioners working to push the boundaries of language-driven human motion synthesis.

  • Open Access

    Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search

    by Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia

    In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.


  • Open Access

    Action Text Diffusion Prior Network for Action Segmentation

    by Danfeng Zhuang, Min Jiang, Hichem Arioui, Hedi Tabia


  • Open Access

    Automated Siamese Network Design for Image Similarity Computation

    by Alexandre Heuillet, Hedi Tabia, Hichem Arioui

    Despite the success of Siamese networks in image indexing, face recognition, and signature verification, there has been little research on designing their architectural space compared to convolutional neural networks (CNNs). This work aims to automate the design process of Siamese network architectures and improve their performance in tasks that involve image similarity computing such as indexing and retrieval. To achieve this goal, in contrast with the current literature that focuses on improving the design of the backbone CNN, we use Differentiable Neural Architecture Search (DNAS) to explore the architecture of the Multi-Layer Perceptron (MLP) component of siamese networks, namely the projector and/or predictor heads. The main objective of these MLPs is to enhance the ability of backbone CNNs to learn strong representations from unlabeled data. Using a well-known contrastive learning framework (SimCLR) as a baseline, we show that our approach managed to improve performance on several computer vision tasks such as image classification (ImageNet) and content-based image retrieval (INRIA Holidays).


  • Open Access

    Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search

    by Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia

    In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS, one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focus specifically on DNAS and review recent approaches in this field. Furthermore, we propose a novel challenge-based taxonomy to classify DNAS methods. We also discuss the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we conclude by giving some insights into future research directions for the DNAS field.

  • FNR-GAN: Face Normalization and Recognition with Generative Adversarial Networks

    by Amina Kammoun, Rim Slama, Hedi Tabia, Tarek Ouni, Mohamed Abid

  • Open Access

    NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks

    by Alexandre Heuillet, Hedi Tabia, Hichem Arioui

    Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled datasets. Meanwhile, Neural Architecture Search (NAS) is becoming increasingly important as a technique to discover novel deep learning architectures. However, early NAS methods based on reinforcement learning or evolutionary algorithms suffered from ludicrous computational and memory costs. In contrast, differentiable NAS, a gradient-based approach, has the advantage of being much more efficient and has thus retained most of the attention in the past few years. In this article, we present NASiam, a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e.g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines. We crafted a search space designed explicitly for multilayer perceptrons, inside which we explored several alternatives to the standard ReLU activation function. We show that these new architectures allow ResNet backbone convolutional models to learn strong representations efficiently. NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours. We discuss the composition of the NAS-discovered architectures and emit hypotheses on why they manage to prevent collapsing behavior. Our code is available at https://github.com/aheuillet/NASiam.

  • Open Access

    Generative Adversarial Networks for Face Generation: A Survey

    by Amina Kammoun, Rim Slama, Hedi Tabia, Tarek Ouni, Mohmed Abid

    Recently, generative adversarial networks (GANs) have progressed enormously, which makes them able to learn complex data distributions in particular faces. More and more efficient GAN architectures have been designed and proposed to learn the different variations of faces, such as cross pose, age, expression, and style. These GAN-based approaches need to be reviewed, discussed, and categorized in terms of architectures, applications, and metrics. Several reviews that focus on the use and advances of GAN in general have been proposed. However, to the best of our knowledge, the GAN models applied to the face, which we call facial GANs , have never been addressed. In this article, we review facial GANs and their different applications. We mainly focus on architectures, problems, and performance evaluation with respect to each application and used datasets. More precisely, we review the progress of architectures and discuss the contributions and limits of each. Then, we expose the encountered problems of facial GANs and propose solutions to handle them. Additionally, as GAN evaluation has become a notable current defiance, we investigate the state-of-the-art quantitative and qualitative evaluation metrics and their applications. We conclude this work with a discussion on the face generation challenges and propose open research issues.