7 papers
Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
Yanick C. Tchenko, Felix Mohr, Hicham Hadj-Abdelkader +1
Efficient perception is central to robotic systems operating under constrained computation, memory, and latency budgets. Knowledge transfer from larger pretrained models offers a p…
Representation learning from OCT images
Hedi Tabia, Désiré Sidibé, Nawres Khlifa +6
Optical Coherence Tomography (OCT) has become one of the most used imaging modality in ophthalmology. It provides high-resolution, non-invasive visualization of retinal microarchit…
HiPP-Prune: Hierarchical Preference-Conditioned Structured Pruning for Vision-Language Models
Lincen Bai, Hedi Tabia, Raul Santos-Rodriguez
Pruning vision-language models (VLMs) for efficient deployment is challenging because compression can affect not only task utility but also visual grounding, often amplifying objec…
Accurate online action and gesture recognition system using detectors and Deep SPD Siamese Networks
Mohamed Sanim Akremi, Rim Slama, Hedi Tabia
Online continuous motion recognition is a hot topic of research since it is more practical in real life application cases. Recently, Skeleton-based approaches have become increasin…
HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
Yanick Chistian Tchenko, Felix Mohr, Hicham Hadj Abdelkader +1
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 th…
Text-driven Motion Generation: Overview, Challenges and Directions
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 pr…
D-DARTS: Distributed Differentiable Architecture Search
Alexandre Heuillet, Hedi Tabia, Hichem Arioui +1
Differentiable ARchiTecture Search (DARTS) is one of the most trending Neural Architecture Search (NAS) methods. It drastically reduces search cost by resorting to weight-sharing.…