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 “"Diffusion Generative Models"”.

  1. Enhancing Histopathology Image Generation with Diffusion Generative Models: A Comprehensive Study

    … and training of effective deep learning models. Generative Adversarial Networks (GANs) have previously attempted to address these issues by creating synthetic data but suffer mode collapse, which reduces their effectiveness and reliability. This study explores Diffusion Generative Models …

    concordia Download PDF for Enhancing Histopathology Image Generation with Diffusion Generative Models: A Comprehensive Study (opens in a new tab)

  2. Towards Efficient and High-Fidelity Generative Models

    Generative models aim to learn the underlying data distribution and synthesize realistic samples such as images, videos, and audio. Deep learning has brought remarkable success to this field, enabling models to capture complex, high-dimensional structures and produce highly realistic outputs. …

    rit Repository record for Towards Efficient and High-Fidelity Generative Models (opens in a new tab)

  3. Toward Causal Generative Modeling: From Representation Learning to Controllable Generation

    … at identifying statistical patterns, current generative models often struggle to capture the underlying structural causal mechanisms of the data-generating process, leaving them vulnerable to shortcut learning and spurious associations. To achieve true generalizability and interpretability, …

    arkansas Repository record for Toward Causal Generative Modeling: From Representation Learning to Controllable Generation (opens in a new tab)

  4. Towards efficient and robust reinforcement learning via synthetic environments and offline data

    … this limitation, we propose <em>Augmented World Models</em>, a novel approach designed for offline-to-online transfer where the test dynamics may differ from the training data. Our method augments a learned dynamics model with simple transformations that seek to capture potential changes in the …

    oxford Repository record for Towards efficient and robust reinforcement learning via synthetic environments and offline data (opens in a new tab)