Salvato in:
Dettagli Bibliografici
Autore principale: Liu, Peng
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:https://arxiv.org/abs/2112.11447
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909020605906944
author Liu, Peng
author_facet Liu, Peng
contents In the context of multi-modality knowledge distillation research, the existing methods was mainly focus on the problem of only learning teacher final output. Thus, there are still deep differences between the teacher network and the student network. It is necessary to force the student network to learn the modality relationship information of the teacher network. To effectively exploit transfering knowledge from teachers to students, a novel modality relation distillation paradigm by modeling the relationship information among different modality are adopted, that is learning the teacher modality-level Gram Matrix.
format Preprint
id arxiv_https___arxiv_org_abs_2112_11447
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
Liu, Peng
Artificial Intelligence
Computer Vision and Pattern Recognition
In the context of multi-modality knowledge distillation research, the existing methods was mainly focus on the problem of only learning teacher final output. Thus, there are still deep differences between the teacher network and the student network. It is necessary to force the student network to learn the modality relationship information of the teacher network. To effectively exploit transfering knowledge from teachers to students, a novel modality relation distillation paradigm by modeling the relationship information among different modality are adopted, that is learning the teacher modality-level Gram Matrix.
title Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2112.11447