Corpus ID: 220265908

Maximum Entropy Models for Fast Adaptation

@article{Sinha2020MaximumEM,
  title={Maximum Entropy Models for Fast Adaptation},
  author={Samarth Sinha and Anirudh Goyal and Animesh Garg},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16524}
}
  • Samarth Sinha, Anirudh Goyal, Animesh Garg
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Deep Neural Networks have shown great promise on a variety of downstream tasks; but their ability to adapt to new data and tasks remains a challenging problem. The ability of a model to perform few-shot adaptation to a novel task is important for the scalability and deployment of machine learning models. Recent work has shown that the learned features in a neural network follow a normal distribution [41], which thereby results in a strong prior on the downstream task. This implicit overfitting… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 85 REFERENCES
    DIBS: Diversity inducing Information Bottleneck in Model Ensembles
    1
    Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
    2130
    Optimization as a Model for Few-Shot Learning
    1125
    Matching Networks for One Shot Learning
    1762
    Deep CORAL: Correlation Alignment for Deep Domain Adaptation
    543
    Meta-Learning without Memorization
    16
    Unsupervised Learning via Meta-Learning
    63
    Meta-Learning with Memory-Augmented Neural Networks
    394
    DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
    4