A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts

Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

344 Scopus citations

Abstract

Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks(GANs) to generate images, we instead leverage GANs to imagine unseen categories from text descriptions and hence recognize novel classes with no examples being seen. Specifically, we propose a simple yet effective generative model that takes as input noisy text descriptions about an unseen class (e.g. Wikipedia articles) and generates synthesized visual features for this class. With added pseudo data, zero-shot learning is naturally converted to a traditional classification problem. Additionally, to preserve the inter-class discrimination of the generated features, a visual pivot regularization is proposed as an explicit supervision. Unlike previous methods using complex engineered regularizers, our approach can suppress the noise well without additional regularization. Empirically, we show that our method consistently outperforms the state of the art on the largest available benchmarks on Text-based Zero-shot Learning.
Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer [email protected]
ISBN (Print)9781538664209
DOIs
StatePublished - Dec 14 2018
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2019-11-20

Fingerprint

Dive into the research topics of 'A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts'. Together they form a unique fingerprint.

Cite this