Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 4 of 4 for “"Stage-wise Training"”.

  1. Conformal Prediction for Time-Series and Flow-Based Generative Models

    … based on the Jordan-Kinderlehrer-Otto scheme for stage-wise training. Finally, Chapter 4 enhances the scalability of ODE-based models by introducing a local flow matching approach, improving training efficiency and distillation performance.

    gatech Repository record for Conformal Prediction for Time-Series and Flow-Based Generative Models (opens in a new tab)

  2. Solving Visual Species Recognition with Open-World Resources

    … and ecology and ecosystem management. However, training such a machine learning model typically requires a large amount of species-level annotated data, which is costly in terms of time, budget, and domain expertise. In addition, observations of species naturally follow a long-tailed …

    tamu Repository record for Solving Visual Species Recognition with Open-World Resources (opens in a new tab)

  3. Solving Visual Species Recognition with Open-World Resources

    … and ecology and ecosystem management. However, training such a machine learning model typically requires a large amount of species-level annotated data, which is costly in terms of time, budget, and domain expertise. In addition, observations of species naturally follow a long-tailed …

    tamu Repository record for Solving Visual Species Recognition with Open-World Resources (opens in a new tab)

  4. Regularizing Deep Models for Visual Recognition

    … representational power of deep networks, training these models is computationally expensive. In addition, considering the lack of enough labeled training data in many applications, over-fitting is a serious threat for deep models with large number of free parameters. Also, there are innate …

    waterloo Repository record for Regularizing Deep Models for Visual Recognition (opens in a new tab)