Lotfi Abdelkrim Mecharbat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Lotfi Abdelkrim Mecharbat has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
Hadjer Benmeziane
Université Polytechnique Hauts-de-France Valenciennes France
1 shared publicationHamza Ouarnoughi
Université Polytechnique Hauts-de-France Valenciennes France
1 shared publicationSmail Niar
Université Polytechnique Hauts-de-France Valenciennes France
1 shared publication
Latest Publications
- Open Access
HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices
Vision Transformers have enabled recent attention-based Deep Learning (DL) architectures to achieve remarkable results in Computer Vision (CV) tasks. However, due to the extensive computational resources required, these architectures are rarely implemented on resource-constrained platforms. Current research investigates hybrid handcrafted convolution-based and attention-based models for CV tasks such as image classification and object detection. In this paper, we propose HyT-NAS, an efficient Hardware-aware Neural Architecture Search (HW-NAS) including hybrid architectures targeting vision tasks on tiny devices. HyT-NAS improves state-of-the-art HW-NAS by enriching the search space and enhancing the search strategy as well as the performance predictors. Our experiments show that HyT-NAS achieves a similar hypervolume with less than ~5x training evaluations. Our resulting architecture outperforms MLPerf MobileNetV1 by 6.3% accuracy improvement with 3.5x less number of parameters on Visual Wake Words.
Open AccessHyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices
Vision Transformers have enabled recent attention-based Deep Learning (DL) architectures to achieve remarkable results in Computer Vision (CV) tasks. However, due to the extensive computational resources required, these architectures are rarely implemented on resource-constrained platforms. Current research investigates hybrid handcrafted convolution-based and attention-based models for CV tasks such as image classification and object detection. In this paper, we propose HyT-NAS, an efficient Hardware-aware Neural Architecture Search (HW-NAS) including hybrid architectures targeting vision tasks on tiny devices. HyT-NAS improves state-of-the-art HW-NAS by enriching the search space and enhancing the search strategy as well as the performance predictors. Our experiments show that HyT-NAS achieves a similar hypervolume with less than ~5x training evaluations. Our resulting architecture outperforms MLPerf MobileNetV1 by 6.3% accuracy improvement with 3.5x less number of parameters on Visual Wake Words.