La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS

Witness identification in multiple instance learning using random subspaces


Téléchargements par mois depuis la dernière année

Plus de statistiques...

Charbonneau, Marc-André et Granger, Éric et Gagnon, Ghyslain. 2016. « Witness identification in multiple instance learning using random subspaces ». In 23rd International Conference on Pattern Recognition (ICPR) (Cancún, México, Dec. 04-08, 2016), p. 3639-3644. IEEE.


Télécharger (415kB) | Prévisualisation


Multiple instance learning (MIL) is a form of weakly-supervised learning where instances are organized in bags. A label is provided for bags, but not for instances. MIL literature typically focuses on the classification of bags seen as one object, or as a combination of their instances. In both cases, performance is generally measured using labels assigned to entire bags. In this paper, the MIL problem is formulated as a knowledge discovery task for which algorithms seek to discover the witnesses (i.e. identifying positive instances), using the weak supervision provided by bag labels. Some MIL methods are suitable for instance classification, but perform poorly in application where the witness rate is low, or when the positive class distribution is multimodal. A new method that clusters data projected in random subspaces is proposed to perform witness identification in these adverse settings. The proposed method is assessed on MIL data sets from three application domains, and compared to 7 reference MIL algorithms for the witness identification task. The proposed algorithm constantly ranks among the best methods in all experiments, while all other methods perform unevenly across data sets.

Type de document: Compte rendu de conférence
Granger, Éric
Gagnon, Ghyslain
Affiliation: Génie de la production automatisée, Génie électrique
Date de dépôt: 16 janv. 2017 21:55
Dernière modification: 10 oct. 2017 17:28
URI: http://espace2.etsmtl.ca/id/eprint/14298

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt