Corpus ID: 220871211

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

@article{Huang2020MultilabelZC,
  title={Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge},
  author={He Huang and Yuan-Wei Chen and W. Tang and Wenhao Zheng and Qingguo Chen and Yao Hu and Philip S. Yu},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.15610}
}
  • He Huang, Yuan-Wei Chen, +4 authors Philip S. Yu
  • Published 2020
  • Computer Science
  • ArXiv
  • Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the model more easily overfit to those seen classes. On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets. To address these difficult issues, this paper introduces a novel multi… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    Deep Residual Learning for Image Recognition
    • 51,641
    • PDF
    Adam: A Method for Stochastic Optimization
    • 50,851
    • Highly Influential
    • PDF
    Microsoft COCO: Common Objects in Context
    • 10,527
    • Highly Influential
    • PDF
    Generative Adversarial Nets
    • 18,171
    • PDF
    Glove: Global Vectors for Word Representation
    • 14,938
    • Highly Influential
    • PDF
    Auto-Encoding Variational Bayes
    • 9,353
    • PDF
    CNN-RNN: A Unified Framework for Multi-label Image Classification
    • 529
    • PDF
    Label-Embedding for Attribute-Based Classification
    • 410
    • Highly Influential
    • PDF
    Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly
    • 374
    • Highly Influential
    • PDF
    Semi-Supervised Classification with Graph Convolutional Networks
    • 4,791
    • Highly Influential
    • PDF