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 “"Generative Classifier"”.

  1. OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION

    … and domain shifts with a non-parametric generative classifier across various DA scenarios. Third, we propose the CoTTA model, which addresses non-stationary OOD data in dynamic environments through a continual test-time adaptation (TTA) framework. Lastly, we tackle open-world OOD …

    nus Repository record for OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION (opens in a new tab) Download file for OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION (opens in a new tab)

  2. Studies of the life history of school sharks (Galeorhinus galeus) : a thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy (PhD) in Ecology at Massey University, Albany, New Zealand

    … and life-history stage data, a novel Bayesian generative classifier model suggested that length at life-history stage transitions varied among several, globally distributed, school shark populations. A study of juvenile school shark growth across several regions in New Zealand (i.e., Kaipara …

    massey Repository record for Studies of the life history of school sharks (Galeorhinus galeus) : a thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy (PhD) in Ecology at Massey University, Albany, New Zealand (opens in a new tab)

  3. Line Based Multi-Range Asymmetric Conditional Random Field For Terrestrial Laser Scanning Data Classification

    … laser scanning mechanism.Ten conventional local classifiers are tested, including popular generative and discriminative classifiers, and experimental results validate that the line-based method can achieve satisfying classification performance. However, local classifiers implement labeling task …

    york Repository record for Line Based Multi-Range Asymmetric Conditional Random Field For Terrestrial Laser Scanning Data Classification (opens in a new tab)

  4. Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness

    … and high accuracy are both key requirements. Generative classifiers, in particular, have been shown to exhibit robustness to out-of-distribution and noisy data, which is an extremely critical consideration for deployment in such real-time edge environments. However, deploying such models on …

    wvu Repository record for Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness (opens in a new tab)