A Multi-Teacher Knowledge Distillation Framework with Aggregation Techniques for Lightweight Deep Models

Knowledge Distillation (KD) is a machine learning technique in which a compact student model learns to replicate the performance of a larger teacher model by mimicking its output predictions. Multi-Teacher Knowledge Distillation extends this paradigm by aggregating knowledge from multiple teacher mo...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Ahmed Hamdi, Hassan N. Noura, Joseph Azar
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-09-01
coleção:	Applied System Innovation
Assuntos:	knowledge distillation cross-modal neural network compression downsampling multi-teachers multi-rounds of distillation
Acesso em linha:	https://www.mdpi.com/2571-5577/8/5/146
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!