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 14 of 14 for “"Conditional GANs"”.

  1. 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)

  2. Improved conditional generative adversarial networks for image generation : methods and their application in knowledge distillation

    Conditional generative adversarial networks (cGANs) are state-of-the-art models for synthesizing images dependent on some conditions. These conditions are usually categorical variables such as class labels. cGANs with class labels as conditions are also known as class-conditional GANs. Some modern …

    ubc Repository record for Improved conditional generative adversarial networks for image generation : methods and their application in knowledge distillation (opens in a new tab) Download PDF for Improved conditional generative adversarial networks for image generation : methods and their application in knowledge distillation (opens in a new tab)

  3. Pseudo-Computed Tomography Image Generation from Magnetic Resonance Imaging Using Generative Adversarial Networks for Veterinary Radiation Therapy Planning

    … canines. A comparative study between two conditional GANs (CGAN), one with a U-Net generator and PatchGAN discriminator, and another with a ResNet U-Net generator and ResNet discriminator are compared. The ResNet U-Net generator and ResNet discriminator produced the most accurate pseudo-CT …

    guelph Repository record for Pseudo-Computed Tomography Image Generation from Magnetic Resonance Imaging Using Generative Adversarial Networks for Veterinary Radiation Therapy Planning (opens in a new tab)

  4. Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation

    … and more. Generative Adversarial Networks (GANs), and in particular Conditional GANs have recently shown incredible success in image-to-image translation and semantic manipulation. However, such methods require paired data, meaning that an image must have ground-truth translations across …

    rit Repository record for Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation (opens in a new tab)

  5. Structural Design Using Conditional-Gan Fused With Property Text Information: A Case for Masonry Structures

    … different collaborations between humans and AI, GANs (Generative Adversarial Networks) are seen to complement human creativity by automating specific facets of the design process. GANs can assist in creating structural designs and exploring the possibilities of different design scenarios. More …

    clemson Repository record for Structural Design Using Conditional-Gan Fused With Property Text Information: A Case for Masonry Structures (opens in a new tab)

  6. Memorization in Generative Networks and Mixtures of GANs

    … Mixtures of generative adversarial networks (GANs) are closely related to subsampling methods. We study these mixtures in the context of memorization and density estimation to show that mixtures of GANs are superior to training a single GAN under certain assumptions. Furthermore, we construct …

    rice Repository record for Memorization in Generative Networks and Mixtures of GANs (opens in a new tab)

  7. The role of generative adversarial networks in bioimage analysis and computational diagnostics.

    … tasks using Generative Adversarial Networks (GANs). For that purpose, several studies were conducted. The first study is on domain translation, where we proposed a digital pathology system that can detect and quantify fibrosis in Hematoxylin and Eosin-stained digital slides. The proposed …

    louisville Repository record for The role of generative adversarial networks in bioimage analysis and computational diagnostics. (opens in a new tab)

  8. Colour technologies for content production and distribution of broadcast content

    … automatic image colourisation paradigm using Conditional GANs is proposed to improve content generalisation and colourfulness of existing baselines. Moreover, a more conservative solution is considered by providing references to guide the system towards more accurate colour predictions. A …

    dcu Download PDF for Colour technologies for content production and distribution of broadcast content (opens in a new tab)

  9. Multi-Modal Deep Learning for Computer Vision and Its Application

    … of both generator and discriminator in conditional GANs to avoid blindly increasing the number of trainable parameters of a network, and construct a single-directional discriminator by combining two training goals (i.e., having better image quality and text-image semantic alignment) into …

    oxford Repository record for Multi-Modal Deep Learning for Computer Vision and Its Application (opens in a new tab)

  10. Learning structure-function interactions of the heart using generative deep learning methods

    … shows that Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) can be used for synthetic 2D Cardiac Magnetic Resonance (CMR) data generation, reaching high levels of image realness that can convince trained observers. It further explores modes of variation within CMR …

    oxford Repository record for Learning structure-function interactions of the heart using generative deep learning methods (opens in a new tab)

  11. Wavelet-based Multi-level GANs for Facial Attributes Editing

    … and backward reconstruction as in current conditional GANs would force the generator to leave a potential "noise" in the generated images, therefore hindering the use of the images for further tasks. To eliminate the interference and break the unwanted link between the first and second …

    concordia Download PDF for Wavelet-based Multi-level GANs for Facial Attributes Editing (opens in a new tab)

  12. Improve the efficiency of conditional generative models

    … a controllable generative process through conditional generative models, which capture the conditional distribution P(X|Y), where X represents high-dimensional data and Y denotes the associated annotation. This controllability makes conditional generative models more preferable than …

    bu Repository record for Improve the efficiency of conditional generative models (opens in a new tab)

  13. Deep Synthetic Noise Generation for RGB-D Data Augmentation

    Considerable effort has been devoted to finding reliable methods of correcting noisy RGB-D images captured with unreliable depth-sensing technologies. Supervised neural networks have been shown to be capable of RGB-D image correction, but require copious amounts of carefully-corrected ground-truth …

    byu Repository record for Deep Synthetic Noise Generation for RGB-D Data Augmentation (opens in a new tab) Download PDF for Deep Synthetic Noise Generation for RGB-D Data Augmentation (opens in a new tab)

  14. Unlocking the potential of artificial intelligence for satellite image processing

    … in DL paired ITIT by typically employing conditional GANs (cGANs) to synthesize missing information in several applications. RGB-to-NIR ITIT, where this thesis focused on, has been either addressed indirectly in the context of creating HS outputs (spectral super-resolution) or has been …

    greece Repository record for Unlocking the potential of artificial intelligence for satellite image processing (opens in a new tab)