Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs
IEEE Access · 2026 · 14 · 59898-59914
DOI: 10.1109/access.2026.3684856 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Chinmaya Kaundanya und 5 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Ireland Insight Centre for Data Analytics at Dublin City University and Luna Systems.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Research Ireland Insight Centre for Data Analytics at Dublin City University and Luna Systems
Zitieren
APA
Kaundanya, C., César, P., Cronin, B., Fleury, A., Liu, M., & Little, S. (2026). Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs. IEEE Access, 14, 59898-59914. https://doi.org/10.1109/access.2026.3684856
Vancouver
Kaundanya C, César P, Cronin B, Fleury A, Liu M, Little S. Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs. IEEE Access. 2026;14:59898-59914. doi:10.1109/access.2026.3684856
BibTeX
@article{Kaundanya2026,
author = {Kaundanya, Chinmaya and César, Paulo and Cronin, Barry and Fleury, Andrew and Liu, Mingming and Little, Suzanne},
title = {Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {59898--59914},
doi = {10.1109/access.2026.3684856}
}
EUVIMED