
Training Compact Deep Learning Models for Video Classification Using Circulant Matrices
Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2018), Training Compact Deep Learning Models for Video Classification Using Circulant Matrices, in Leal-Taixé, Laura; Roth, Stefan, Computer Vision – ECCV 2018 Workshops, Proceedings, Springer : Berlin Heidelberg, p. 271-286. 10.1007/978-3-030-11018-5
View/ Open
Type
Communication / ConférenceDate
2018Conference title
15th European Conference on Computer Vision (ECCV 2018)Conference date
2018-09Conference city
MunichConference country
GermanyBook title
Computer Vision – ECCV 2018 Workshops, ProceedingsBook author
Leal-Taixé, Laura; Roth, StefanPublisher
Springer
Published in
Berlin Heidelberg
ISBN
978-3-030-11017-8
Pages
271-286
Publication identifier
Metadata
Show full item recordAuthor(s)
Araújo, AlexandreLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Negrevergne, Benjamin

Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Chevaleyre, Yann
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Atif, Jamal
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)
In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which make them difficult to train and to deploy, especially on mobile devices. In this paper, we build on recent results at the crossroads of Linear Algebra and Deep Learning which demonstrate how imposing a structure on large weight matrices can be used to reduce the size of the model. Building on these results, we propose very compact models for video classification based on state-of-the-art network architectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVectors. We then conduct thorough experiments using the large YouTube-8M video classification dataset. As we will show, the circulant DBoF embedding achieves an excellent trade-off between size and accuracy.Subjects / Keywords
Deep learning; Computer vision; Structured matrices; Circulant matricesRelated items
Showing items related by title and author.
-
Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2019) Document de travail / Working paper
-
Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2021) Communication / Conférence
-
Araujo, Alexandre (2021-06-01) Thèse
-
Thanh Hai, Nguyen; Chevaleyre, Yann; Prifti, Edi; Sokolovska, Nataliya; Zucker, Jean-Daniel (2017) Communication / Conférence
-
Meunier, Laurent; Ettedgui, Raphael; Pinot, Rafael; Chevaleyre, Yann; Atif, Jamal (2022) Communication / Conférence