Skip to Main content Skip to Navigation
New interface
Conference papers

Context-Aware Zero-Shot Learning for Object Recognition

Abstract : Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge , such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the surrounding objects in the image, is ignored. Following the intuitive principle that objects tend to be found in certain contexts but not others, we propose a new and challenging approach, context-aware ZSL, that leverages semantic representations in a new way to model the conditional likelihood of an object to appear in a given context. Finally, through extensive experiments conducted on Visual Genome, we show that contextual information can substantially improve the standard ZSL approach and is robust to unbalanced classes.
Complete list of metadata

Cited literature [63 references]  Display  Hide  Download
Contributor : eloi zablocki Connect in order to contact the contributor
Submitted on : Wednesday, May 1, 2019 - 11:45:02 AM
Last modification on : Sunday, June 26, 2022 - 2:37:59 AM
Long-term archiving on: : Monday, September 30, 2019 - 6:15:14 PM


Files produced by the author(s)


  • HAL Id : hal-02116654, version 1


Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari. Context-Aware Zero-Shot Learning for Object Recognition. Thirty-sixth International Conference on Machine Learning (ICML), Jun 2019, Long Beach, CA, United States. ⟨hal-02116654⟩



Record views


Files downloads