Hard Negative Mining for Metric Learning Based Zero-Shot Classification

Maxime Bucher 1, 2 Stéphane Herbin 1 Frédéric Jurie 2
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.
Liste complète des métadonnées

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01356757
Contributor : Maxime Bucher <>
Submitted on : Friday, August 26, 2016 - 1:42:00 PM
Last modification on : Tuesday, April 2, 2019 - 1:36:15 AM
Document(s) archivé(s) le : Sunday, November 27, 2016 - 12:36:38 PM

Files

1-paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01356757, version 1
  • ARXIV : 1608.07441

Citation

Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Hard Negative Mining for Metric Learning Based Zero-Shot Classification. ECCV 16 WS TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision, Oct 2016, Amsterdam, Netherlands. ⟨hal-01356757⟩

Share

Metrics

Record views

609

Files downloads

413