Model Selection for Generalized Zero-shot Learning

@article{Zhang2018ModelSF,
  title={Model Selection for Generalized Zero-shot Learning},
  author={Hongguang Zhang and Piotr Koniusz},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.03252}
}
  • Hongguang Zhang, Piotr Koniusz
  • Published in ECCV Workshops 2018
  • Computer Science
  • ArXiv
  • In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the classifier to distinguish if a given testing sample comes from a seen or unseen class. However, using Generative Adversarial Network (GAN) to generate auxiliary datapoints by the semantic embeddings of unseen classes alleviates the above problem. Current… CONTINUE READING
    2
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.
    SHOWING 1-6 OF 6 CITATIONS

    Generative Adversarial Data Programming

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Long-tail learning with attributes

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Few-Shot Learning via Saliency-Guided Hallucination of Samples

    VIEW 1 EXCERPT
    CITES METHODS

    Power Normalizing Second-Order Similarity Network for Few-Shot Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES

    Zero-Shot Learning — The Good, the Bad and the Ugly

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Automated Flower Classification over a Large Number of Classes

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Feature Generating Networks for Zero-Shot Learning

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Zero-Shot Kernel Learning

    VIEW 2 EXCERPTS

    Power Normalizing Second-Order Similarity Network for Few-Shot Learning

    VIEW 1 EXCERPT

    A Deeper Look at Power Normalizations

    VIEW 1 EXCERPT

    Semantic Autoencoder for Zero-Shot Learning

    Latent Embeddings for Zero-Shot Classification

    Synthesized Classifiers for Zero-Shot Learning