Training compact deep learning models for video classification using circulant matrices

Alexandre Araujo (1, 2) , Benjamin Negrevergne (2, 1) , Yann Chevaleyre (2, 1) , Jamal Atif (2)

1 MILES - Machine Intelligence and Learning Systems
2 LAMSADE - Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision

In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes 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. 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.

Mots clés: Structured matrices; Deep Learning; Computer Vision; Video Classification

Domaines: Informatique [cs]; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]

Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif. Training compact deep learning models for video classification using circulant matrices. European Conference on Computer Vision, 2018, pp.271-286. ⟨10.1007/978-3-030-11018-5_25⟩. ⟨hal-02010093⟩