I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation

Autor: Karine, Ayoub, Napoléon, Thibault, Jridi, Maher

This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the intermedia

Externí odkaz: http://arxiv.org/abs/2403.18490

Channel-spatial knowledge distillation for efficient semantic segmentation

Autor: Karine, Ayoub ^{a, ⁎}, Napoléon, Thibault ^b, Jridi, Maher ^a

Publikováno v: In Pattern Recognition Letters April 2024 180:48-54

Pose invariant face recognition: 3D model from single photo

Autor: Napoléon, Thibault ^⁎, Alfalou, Ayman ^⁎⁎

Publikováno v: In Optics and Lasers in Engineering February 2017 89:150-161

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

SHREC'08 entry: Multi-view 3D retrieval using multi-scale contour representation

Autor: Napoleon, Thibault, Adamek, Tomasz, Schmitt, Francis, O'Connor, Noël

Publikováno v: 2008 IEEE International Conference on Shape Modeling and Applications (SMI)
2008 IEEE International Conference on Shape Modeling and Applications (SMI), Jun 2008, Stony Brook, United States. pp.227-228, ⟨10.1109/SMI.2008.4547980⟩

International audience; We describe in this paper a method for 3D shape indexing and retrieval that we apply on three data collections of the SHREC - SHape Retrieval Contest 2008: Stability on watertight, CAD and Generic 3D models. The method is base

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b99008c171e90776b100123b54f431c3
https://hal.archives-ouvertes.fr/hal-02562040