Mining on Manifolds: Metric Learning without Labels - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Mining on Manifolds: Metric Learning without Labels

Abstract

In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds. Both types of examples are revealed by disagreements between Euclidean and manifold similarities. The discovered examples can be used in training with any discriminative loss. The method is applied to unsupervised fine-tuning of pre-trained networks for fine-grained classification and particular object retrieval. Our models are on par or are outperforming prior models that are fully or partially supervised.
Fichier principal
Vignette du fichier
C108.cvpr18.mom.pdf (8.73 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01843085 , version 1 (18-07-2018)

Identifiers

  • HAL Id : hal-01843085 , version 1

Cite

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum. Mining on Manifolds: Metric Learning without Labels. CVPR 2018 - IEEE Computer Vision and Pattern Recognition Conference, Jun 2018, Salt Lake City, United States. pp.1-10. ⟨hal-01843085⟩
260 View
101 Download

Share

Gmail Facebook X LinkedIn More