Hard Negative Mining for Metric Learning Based Zero-Shot Classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Hard Negative Mining for Metric Learning Based Zero-Shot Classification

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.
Fichier principal
Vignette du fichier
1-paper.pdf (276.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01356757 , version 1 (26-08-2016)

Identifiers

Cite

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⟩
456 View
701 Download

Altmetric

Share

Gmail Facebook X LinkedIn More