Good Practice in Large-Scale Learning for Image Classification

Zeynep Akata 1, 2 Florent Perronnin 1 Zaid Harchaoui 2 Cordelia Schmid 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We benchmark several SVM objective functions for large-scale image classification. We consider one-vs-rest, multi-class, ranking, and weighted approximate ranking SVMs. A comparison of online and batch methods for optimizing the objectives shows that online methods perform as well as batch methods in terms of classification accuracy, but with a significant gain in training speed. Using stochastic gradient descent, we can scale the training to millions of images and thousands of classes. Our experimental evaluation shows that ranking-based algorithms do not outperform the one-vs-rest strategy when a large number of training examples are used. Furthermore, the gap in accuracy between the different algorithms shrinks as the dimension of the features increases. We also show that learning through cross-validation the optimal rebalancing of positive and negative examples can result in a significant improvement for the one-vs-rest strategy. Finally, early stopping can be used as an effective regularization strategy when training with online algorithms. Following these "good practices", we were able to improve the state-of-the-art on a large subset of 10K classes and 9M images of ImageNet from 16.7% Top-1 accuracy to 19.1%.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2014, 36 (3), pp.507-520. 〈10.1109/TPAMI.2013.146〉
Liste complète des métadonnées

Littérature citée [88 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00835810
Contributeur : Thoth Team <>
Soumis le : mercredi 19 juin 2013 - 17:07:44
Dernière modification le : mardi 11 août 2015 - 01:05:15
Document(s) archivé(s) le : vendredi 20 septembre 2013 - 04:07:57

Fichiers

TPAMI_minor_revision.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid. Good Practice in Large-Scale Learning for Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2014, 36 (3), pp.507-520. 〈10.1109/TPAMI.2013.146〉. 〈hal-00835810〉

Partager

Métriques

Consultations de
la notice

2763

Téléchargements du document

9527