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 metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02116654
Contributor : Eloi Zablocki <>
Submitted on : Wednesday, May 1, 2019 - 11:45:02 AM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM

File

1904.12638.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02116654, version 1

Citation

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⟩

Share

Metrics

Record views

61

Files downloads

50