Transformation Pursuit for Image Classification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Transformation Pursuit for Image Classification

Mattis Paulin
  • Fonction : Auteur
  • PersonId : 956055
Jérôme Revaud
  • Fonction : Auteur
  • PersonId : 946914
Zaid Harchaoui
  • Fonction : Auteur
  • PersonId : 895242
Florent Perronnin
  • Fonction : Auteur
  • PersonId : 928545
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

A simple approach to learning invariances in image classification consists in augmenting the training set with transformed versions of the original images. However, given a large set of possible transformations, selecting a compact subset is challenging. Indeed, all transformations are not equally informative and adding uninformative transformations increases training time with no gain in accuracy. We propose a principled algorithm – Image Transformation Pursuit (ITP) – for the automatic selection of a compact set of transformations. ITP works in a greedy fashion, by selecting at each iteration the one that yields the highest accuracy gain. ITP also allows to efficiently explore complex transformations, that combine basic transformations. We report results on two public benchmarks: the CUB dataset of bird images and the ImageNet 2010 challenge. Using Fisher Vector representations, we achieve an improvement from 28.2% to 45.2% in top-1 accuracy on CUB, and an improvement from 70.1% to 74.9% in top-5 accuracy on ImageNet. We also show significant improvements for deep convnet features: from 47.3% to 55.4% on CUB and from 77.9% to 81.4% on ImageNet.
Fichier principal
Vignette du fichier
paulin_ITP_cvpr2014.pdf (435.16 Ko) Télécharger le fichier
Vignette du fichier
transformations_thumb.jpg (244.95 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Figure, Image
Loading...

Dates et versions

hal-00979464 , version 1 (16-04-2014)

Identifiants

Citer

Mattis Paulin, Jérôme Revaud, Zaid Harchaoui, Florent Perronnin, Cordelia Schmid. Transformation Pursuit for Image Classification. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. pp.3646-3653, ⟨10.1109/CVPR.2014.466⟩. ⟨hal-00979464⟩
2758 Consultations
5161 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More