Generating Visual Representations for 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 : This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to as the Zero-Shot classification task (ZSC). Most of the previous methods rely on learning a common embedding space allowing to compare visual features of unknown categories with semantic descriptions. This paper argues that these approaches are limited as i) efficient discrimi-native classifiers can't be used ii) classification tasks with seen and unseen categories (Generalized Zero-Shot Classification or GZSC) can't be addressed efficiently. In contrast , this paper suggests to address ZSC and GZSC by i) learning a conditional generator using seen classes ii) generate artificial training examples for the categories without exemplars. ZSC is then turned into a standard supervised learning problem. Experiments with 4 generative models and 5 datasets experimentally validate the approach, giving state-of-the-art results on both ZSC and GZSC.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01576222
Contributor : Maxime Bucher <>
Submitted on : Monday, December 11, 2017 - 4:14:56 PM
Last modification on : Tuesday, April 2, 2019 - 1:36:23 AM

Files

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

Identifiers

  • HAL Id : hal-01576222, version 3
  • ARXIV : 1708.06975

Citation

Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Generating Visual Representations for Zero-Shot Classification. International Conference on Computer Vision (ICCV), Oct 2017, venise, Italy. ⟨hal-01576222v3⟩

Share

Metrics

Record views

171

Files downloads

364