Zero-Shot Classification by Generating Artificial Visual Features

Maxime Bucher 1 Stéphane Herbin 2 Frédéric Jurie 3
3 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 (visual attributes) while the others are also defined by exemplar images. This task is often referred to as Zero-Shot classification (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 discriminative classi-fiers can't be used and ii) classification tasks with seen and unseen categories (Generalized Zero-Shot Classification or GZSC) can't be addressed efficiently. 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 therefore turned into a standard supervised learning problem. Experiments with 4 generative models and 6 datasets experimentally validate the approach, giving state-of-the-art results on both ZSC and GZSC.
Complete list of metadatas
Contributor : Maxime Bucher <>
Submitted on : Sunday, May 20, 2018 - 4:16:29 PM
Last modification on : Tuesday, April 2, 2019 - 1:34:41 AM
Long-term archiving on : Monday, September 24, 2018 - 8:42:52 PM


Files produced by the author(s)


  • HAL Id : hal-01796440, version 1


Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Zero-Shot Classification by Generating Artificial Visual Features. RFIAP, Jun 2018, Paris, France. ⟨hal-01796440⟩



Record views


Files downloads