CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval

Résumé

We propose a novel Coupled Projection multi-task Metric Learning (CP-mtML) method for large scale face retrieval. In contrast to previous works which were limited to low dimensional features and small datasets, the proposed method scales to large datasets with high dimensional face descriptors. It utilises pairwise (dis-)similarity constraints as supervision and hence does not require exhaustive class annotation for every training image. While, traditionally, multi-task learning methods have been validated on same dataset but different tasks, we work on the more challenging setting with heterogeneous datasets and different tasks. We show empirical validation on multiple face image datasets of different facial traits, e.g. identity, age and expression. We use classic Local Binary Pattern (LBP) de-scriptors along with the recent Deep Convolutional Neural Network (CNN) features. The experiments clearly demonstrate the scalability and improved performance of the proposed method on the tasks of identity and age based face image retrieval compared to competitive existing methods, on the standard datasets and with the presence of a million distractor face images.
Fichier principal
Vignette du fichier
mtml_cvpr2016.pdf (1.98 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01301381 , version 1 (12-04-2016)

Identifiants

  • HAL Id : hal-01301381 , version 1

Citer

Binod Bhattarai, Gaurav Sharma, Frédéric Jurie. CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval. 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Jun 2016, Las Vegas, NV, United States. ⟨hal-01301381⟩
1553 Consultations
305 Téléchargements

Partager

Gmail Facebook X LinkedIn More