Corpus ID: 67749964

Adaptive Cross-Modal Few-Shot Learning

@article{Xing2019AdaptiveCF,
  title={Adaptive Cross-Modal Few-Shot Learning},
  author={Chen Xing and N. Rostamzadeh and Boris N. Oreshkin and Pedro H. O. Pinheiro},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.07104}
}
  • Chen Xing, N. Rostamzadeh, +1 author Pedro H. O. Pinheiro
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, visual features might be richer and more discriminative than text ones. While for others, the inverse might be true. Moreover, when the support from visual information is limited in… CONTINUE READING
    41 Citations

    Figures, Tables, and Topics from this paper

    Learning Class Prototypes Via Anisotropic Combination of Aligned Modalities for Few-Shot Learning
    • Highly Influenced
    Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition
    • PDF
    Few-shot Learning with Contextual Cueing for Object Recognition in Complex Scenes
    • 1
    • Highly Influenced
    Looking back to lower-level information in few-shot learning
    • 1
    • PDF
    Prototype Completion with Primitive Knowledge for Few-Shot Learning
    • PDF
    Towards Contextual Learning in Few-shot Object Classification
    • Highly Influenced
    • PDF
    Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
    • 9
    • PDF
    Improved Few-Shot Visual Classification
    • 11
    • PDF
    Pseudo Shots: Few-Shot Learning with Auxiliary Data
    • PDF
    Learning from Few Samples: A Survey
    • 4
    • PDF

    References

    SHOWING 1-10 OF 71 REFERENCES
    Learning Robust Visual-Semantic Embeddings
    • 87
    • PDF
    Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
    • 135
    • PDF
    Learning Compositional Representations for Few-Shot Recognition
    • 33
    • PDF
    Meta-Learning for Semi-Supervised Few-Shot Classification
    • 335
    • Highly Influential
    • PDF
    Learning to Compare: Relation Network for Few-Shot Learning
    • 959
    • Highly Influential
    • PDF
    Zero-Shot Learning Through Cross-Modal Transfer
    • 963
    • PDF
    TADAM: Task dependent adaptive metric for improved few-shot learning
    • 359
    • PDF
    Low-Shot Learning from Imaginary Data
    • 274
    • PDF
    Matching Networks for One Shot Learning
    • 2,146
    • Highly Influential
    • PDF