Hash-Based Support Vector Machines Approximation for Large Scale Prediction

Saloua Litayem Ouertani (1, 2) , Alexis Joly (2) , Nozha Boujemaa (3)

1 IMEDIA2 - Images et multimédia : indexation, navigation et recherche
2 ZENITH - Scientific Data Management
3 Inria Saclay - Ile de France

How-to train effective classifiers on huge amount of multimedia data is clearly a major challenge that is attracting more and more research works across several communities. Less efforts however are spent on the counterpart scalability issue: how to apply big trained models efficiently on huge non annotated media collections ? In this paper, we address the problem of speeding-up the prediction phase of linear Support Vector Machines via Locality Sensitive Hashing. We propose building efficient hash based classifiers that are applied in a first stage in order to approximate the exact results and filter the hypothesis space. Experiments performed with millions of one-against-one classifiers show that the proposed hash-based classifier can be more than two orders of magnitude faster than the exact classifier with minor losses in quality.

Mots clés: hashing methods; LSH; SVM

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Saloua Litayem Ouertani, Alexis Joly, Nozha Boujemaa. Hash-Based Support Vector Machines Approximation for Large Scale Prediction. BMVC: British Machine Vision Conference, Sep 2012, Surrey, United Kingdom. pp.86.1-86.11. ⟨hal-00733912⟩