Evaluation of Continuous Image Features Learned by ODE Nets

@inproceedings{Carrara2019EvaluationOC,
  title={Evaluation of Continuous Image Features Learned by ODE Nets},
  author={Fabio Carrara and G. Amato and F. Falchi and C. Gennaro},
  booktitle={ICIAP},
  year={2019}
}
  • Fabio Carrara, G. Amato, +1 author C. Gennaro
  • Published in ICIAP 2019
  • Computer Science
  • Deep-learning approaches in data-driven modeling relies on learning a finite number of transformations (and representations) of the data that are structured in a hierarchy and are often instantiated as deep neural networks (and their internal activations). State-of-the-art models for visual data usually implement deep residual learning: the network learns to predict a finite number of discrete updates that are applied to the internal network state to enrich it. Pushing the residual learning… CONTINUE READING
    1 Citations
    Continuous ODE-defined Image Features for Adaptive Retrieval

    References

    SHOWING 1-10 OF 33 REFERENCES
    Stable Architectures for Deep Neural Networks
    • 204
    • PDF
    Neural Ordinary Differential Equations
    • 736
    • PDF
    Deep Neural Networks Motivated by Partial Differential Equations
    • 134
    • PDF
    Identity Mappings in Deep Residual Networks
    • 4,062
    • PDF
    End-to-End Learning of Deep Visual Representations for Image Retrieval
    • 252
    • PDF
    From generic to specific deep representations for visual recognition
    • 323
    • PDF
    Deep Residual Learning for Image Recognition
    • 53,474
    • PDF