Leveraging the Invariant Side of Generative Zero-Shot Learning

@article{Li2019LeveragingTI,
  title={Leveraging the Invariant Side of Generative Zero-Shot Learning},
  author={J. Li and Mengmeng Jing and K. Lu and Z. Ding and Lei Zhu and Zi Huang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={7394-7403}
}
  • J. Li, Mengmeng Jing, +3 authors Zi Huang
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Conventional zero-shot learning (ZSL) methods generally learn an embedding, e.g., visual-semantic mapping, to handle the unseen visual samples via an indirect manner. In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions. Specifically, we train a conditional Wasserstein GANs in… CONTINUE READING
    Bi-Semantic Reconstructing Generative Network for Zero-shot Learning
    1
    Alleviating Feature Confusion for Generative Zero-shot Learning
    7
    GT-GAN: A General Transductive Zero-Shot Learning Method Based on GAN
    Generative Adversarial Zero-shot Learning via Knowledge Graphs
    1
    Invertible Zero-Shot Recognition Flows
    2
    Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES
    A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
    137
    Generative Zero-Shot Learning via Low-Rank Embedded Semantic Dictionary
    21
    Feature Generating Networks for Zero-Shot Learning
    254
    Semantic Autoencoder for Zero-Shot Learning
    333
    Generalized Zero-Shot Learning via Synthesized Examples
    164
    Learning a Deep Embedding Model for Zero-Shot Learning
    268
    Synthesized Classifiers for Zero-Shot Learning
    403
    Zero-Shot Learning via Joint Latent Similarity Embedding
    246
    From Zero-Shot Learning to Cold-Start Recommendation
    20