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 20 of 51 for “"conditional generative adversarial network"”.

  1. Cell-conditional generative adversarial network

    … We constructed and optimized a stand-alone cell-conditional GAN (ccGAN) to simulate cell-specific ATAC-seq data. We trained our model on published single cell ATAC-seq (scATAC-seq) data that had been produced with different protocols on embryonic mice forebrain and adult mice brain. The ccGAN …

    ubc Repository record for Cell-conditional generative adversarial network (opens in a new tab) Download PDF for Cell-conditional generative adversarial network (opens in a new tab)

  2. Unpaired Style Transfer Conditional Generative Adversarial Network for Scanned Document Generation

    Neural networks are a powerful machine learning tool, especially when trained on a large dataset of relevant high-quality data. Generative adversarial networks, image super resolution and most other image manipulation neural networks require a dataset of images and matching target images for …

    portland-state Repository record for Unpaired Style Transfer Conditional Generative Adversarial Network for Scanned Document Generation (opens in a new tab)

  3. Comparison of methods for creating populations of models by solving stochastic inverse problems

    … inverse problems. In recent years, however, Generative Adversarial Networks (GANs) have been employed. The effectiveness of Markov Chain Monte Carlo methods as compared to a conditional generative adversarial network (cGAN) when applied to a family of models produced by a system of ordinary …

    njit Repository record for Comparison of methods for creating populations of models by solving stochastic inverse problems (opens in a new tab)

  4. Adapting Deep Learning for Underwater Acoustic Communication Channel Modeling

    … for underwater acoustic (UWA) communication and networking techniques. However, due to the challenging UWA channel characteristics, conventional wireless techniques are rarely applicable to UWA communication and networking. The cognitive and software-defined communication and networking are …

    mtu Repository record for Adapting Deep Learning for Underwater Acoustic Communication Channel Modeling (opens in a new tab)

  5. Sensor Modelling with Recurrent Conditional GANs

    … thesis we have developed and used the Recurrent Conditional Generative Adversarial Network (RCGAN) in order to model the longitudinal error of sensors. The RCGAN is a modification of the original generative adversarial network (GAN) framework which makes use of recurrent neural networks and …

    chalmers Repository record for Sensor Modelling with Recurrent Conditional GANs (opens in a new tab)

  6. Cervical Cell Separation using Deep Learning Techniques

    … technique, which is a cascaded deep learning network comprising the Meta-Polyp model and a modified U-Net model employing transfer learning from a pretrained backbone network. The proposed segmentation pipeline's application is extended to obtain the union mask of overlapping cells. The …

    carleton Repository record for Cervical Cell Separation using Deep Learning Techniques (opens in a new tab)

  7. Object Detection and Classification in the Visible and Infrared Spectrums

    … in thermal imagery, a custom convolutional network architecture is proposed for small thermal target detection. For the second scenario, thermal face landmark detection and thermal cross-spectral face verification, a publicly-available visible and thermal face dataset is introduced, along …

    wvu Repository record for Object Detection and Classification in the Visible and Infrared Spectrums (opens in a new tab)

  8. Bacterial Deepfakes: Generating Synthetic Microscopy Data to Improve Adaptability of Deep Learning-Based Segmentation Models

    … images. We introduce OmniStyle, a custom conditional-generative-adversarial network (CGAN) for generating annotated synthetic images to artificially increase the size and/or diversity of training datasets. We demonstrate that training with images generated by OmniStyle improves …

    washington Repository record for Bacterial Deepfakes: Generating Synthetic Microscopy Data to Improve Adaptability of Deep Learning-Based Segmentation Models (opens in a new tab)

  9. Emotion detection with privacy preservation using adversarial learning

    … landmarks. We then propose a modification of a conditional generative adversarial network that can transform facial images in such a way that the identity based information is ignored while the emotion based information is retained. We then evaluate the degree of emotion and identity content in …

    tamu Repository record for Emotion detection with privacy preservation using adversarial learning (opens in a new tab)

  10. Imagerie ultrasonore par réseaux antagonistes génératifs conditionnels (cGAN)

    … adversaire génératif conditionnel (de l’anglais conditional Generative Adversarial Network : cGAN) en combinaison avec des acquisitions type onde plane à zéro degré. Dans ce mémoire, trois différents modèles de cGAN ont été testés avec différentes fonctions de coût dans trois configurations …

    ets-quebec Download PDF for Imagerie ultrasonore par réseaux antagonistes génératifs conditionnels (cGAN) (opens in a new tab)

  11. TransFURmer: Hair and Fur rendering using SwinIR - Transformer-based Neural Rendering of Hair and Fur using SwinIR

    … A SwinIR-based architecture is adapted within a Conditional Generative Adversarial Network (CGAN) framework to translate input buffers into high-quality renders. Trained on the SyntheticFur dataset, the model utilizes a combination of losses, notably Frequency Domain (FFT) loss, Learned …

    chalmers Repository record for TransFURmer: Hair and Fur rendering using SwinIR - Transformer-based Neural Rendering of Hair and Fur using SwinIR (opens in a new tab)

  12. Towards a more robust machine learning framework for computer-assisted echocardiography

    … integrating recurrent fully convolutional neural networks and optical flow estimation maps to accurately track the left ventricle in echo video clips. We also propose a semi-supervised learning algorithm to leverage unlabeled data to improve the performance of machine learning methods. Moreover, …

    ubc Repository record for Towards a more robust machine learning framework for computer-assisted echocardiography (opens in a new tab) Download PDF for Towards a more robust machine learning framework for computer-assisted echocardiography (opens in a new tab)

  13. Studies of Algorithmic Music Generation; Folksong Enthusiasm in Post-Cultural Revolution China

    … the image generation technique known as the conditional Generative Adversarial Network. Experiments with these techniques yielded two musical pieces—an electronic piano piece and a string quartet—both of which are included in the chapter and deemed to meet professional compositional …

    duke Repository record for Studies of Algorithmic Music Generation; Folksong Enthusiasm in Post-Cultural Revolution China (opens in a new tab) Embargoed until 2029-05-21

  14. A deep learning pipeline for real-time palliative radiotherapy of spine metastasis

    … begins with image quality enhancements using a conditional generative adversarial network (GAN)-based network for reducing streaking artifacts and a cycle-consistent GAN for CBCT-based sCT generation. Subsequent phases involve a three-stage network for vertebral segmentation, using heatmap …

    carleton Repository record for A deep learning pipeline for real-time palliative radiotherapy of spine metastasis (opens in a new tab)

  15. Securing Wide-area Damping Controls in the Presence of Inverter-Based Resources

    … detection approach based on a modified conditional generative adversarial network (MCGAN) is proposed, enabling improved performance under limited and imbalanced datasets. In addition, an alternative model-based defense strategy based on a cooperative control is introduced to maintain …

    concordia Download PDF for Securing Wide-area Damping Controls in the Presence of Inverter-Based Resources (opens in a new tab)

  16. OPTICAL COHERENCE TOMOGRAPHY BASED OPHTHALMIC AND GASTROINTESTINAL SURGICAL GUIDANCE USING DEEP LEARNING

    … analyzing the intestinal perfusion level. The conditional generative adversarial network (cGAN) was utilized for perform dual-modality image alignment and translation during the swine model study. Moreover, by integrating the fiber probe with STAR system, OCT guided suturing procedure was …

    jhu Repository record for OPTICAL COHERENCE TOMOGRAPHY BASED OPHTHALMIC AND GASTROINTESTINAL SURGICAL GUIDANCE USING DEEP LEARNING (opens in a new tab)

  17. Synthetic data generation methods and their application to incomplete experimental design /

    … overcome this limitation, a framework based on conditional generative adversarial network (cGAN) was employed to generate synthetic Mel spectrograms based on contextual information. The proposed methodology involves preprocessing raw vibration signals by injecting Laplace noise, segmenting them …

    vilnius Repository record for Synthetic data generation methods and their application to incomplete experimental design / (opens in a new tab)

  18. Computational Approaches in the Humanities: from Sentiment Analysis to Deep Learning Colorization

    … dataset with the pix2pix model, which is a conditional generative adversarial network (cGAN) model, to verify the dataset for colorizing black-and-white illustrations from the nineteenth century. Chapter 2, “Case Study: Using Machine-Colored Illustrations of Charles Dickens’s Fiction in the …

    tamu Repository record for Computational Approaches in the Humanities: from Sentiment Analysis to Deep Learning Colorization (opens in a new tab)

  19. Post-processing East African precipitation forecasts using a generative machine learning model

    … a state-of-the-art machine learning method (a conditional Generative Adversarial Network, cGAN) to postprocess precipitation forecasts in the UK, we present a novel way to improve precipitation forecasts in East Africa. We address the challenge of realistically representing tropical convective …

    bristol Repository record for Post-processing East African precipitation forecasts using a generative machine learning model (opens in a new tab) Download PDF for Post-processing East African precipitation forecasts using a generative machine learning model (opens in a new tab)

Page 1 of 3