Grafit: Learning fine-grained image representations with coarse labels - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Grafit: Learning fine-grained image representations with coarse labels

Matthieu Cord

Résumé

This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection annotated with coarse labels only. Our network is learned with a nearest-neighbor classifier objective, and an instance loss inspired by selfsupervised learning. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods. Our strategy outperforms all competing methods for retrieving or classifying images at a finer granularity than that available at train time. It also improves the accuracy for transfer learning tasks to fine-grained datasets.
Fichier non déposé

Dates et versions

hal-03997922 , version 1 (20-02-2023)

Identifiants

  • HAL Id : hal-03997922 , version 1

Citer

Matthieu Cord. Grafit: Learning fine-grained image representations with coarse labels. ICCV, Oct 2021, Montréal, Canada. ⟨hal-03997922⟩
8 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More