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 9 of 9 for “"Transposed convolution"”.

  1. GAN-Based Super-Resolution And Segmentation Of Retinal Layers In Optical Coherence Tomography Scans

    … the GAN architecture with additional blocks of transposed convolution and sub-pixel convolution for the task of upscaling OCT images from low to high resolution by a factor of four. We also incorporate the Dice loss as an additional reconstruction loss term to improve the performance of this …

    wvu Repository record for GAN-Based Super-Resolution And Segmentation Of Retinal Layers In Optical Coherence Tomography Scans (opens in a new tab)

  2. Deep Learning on Hyperspectral Image Classification

    … Since last decade, the intensive employment of Convolutional Neural Networks (CNN) for classification and segmentation tasks led to high-quality results in the field of Hyperspectral Imagery Classification. However, these works are not able to perform satisfactorily on data acquired from various …

    catania Repository record for Deep Learning on Hyperspectral Image Classification (opens in a new tab)

  3. Mitigating computational bottlenecks in deep neural networks through reduced-precision hardware and software

    … a model would enable us to offset the cost of transposed-convolution decoders with a sequence of lightweight matrix outer products.

    iastate Repository record for Mitigating computational bottlenecks in deep neural networks through reduced-precision hardware and software (opens in a new tab)

  4. Hardware-software co-design of FPGA-based neural network accelerators for edge inference

    … of the MM2IM architecture for accelerating Transposed Convolution (TCONV) operations within Generative Adversarial Networks (GANs) for resource-constrained edge devices. This architecture was developed utilising the SECDA methodology and the SECDA-TFLite toolkit. The MM2IM accelerator …

    glasgow Repository record for Hardware-software co-design of FPGA-based neural network accelerators for edge inference (opens in a new tab) Download PDF for Hardware-software co-design of FPGA-based neural network accelerators for edge inference (opens in a new tab)

  5. Automation of Luminescence Quantitation for High-Throughput Plant Phenotyping Using Image Processing and Deep Learning

    … targeted leaf. Secondly, UNet, an evolution of Convolutional Neural Network (CNN) is used to segment the leaf mask at equal resolution as the input image. The U-Net architecture has a shrinking or down-sampling path and expanding or up-sampling path. The down-sampling path shadows the …

    texas-state Repository record for Automation of Luminescence Quantitation for High-Throughput Plant Phenotyping Using Image Processing and Deep Learning (opens in a new tab)

  6. In-Memory Computing Architecture for Deep Learning Acceleration

    … underutilization due to a new operator, namely, transposed convolution, used in unsupervised learning models. ZARA improves the system efficiency by a novel computation deformation technique. In the third work, I present MARVEL that targets to improve power efficiency in previous resistive …

    duke Repository record for In-Memory Computing Architecture for Deep Learning Acceleration (opens in a new tab)

  7. Spectral-Spatial Neural Networks and Probabilistic Graph Models for Hyperspectral Image Classification

    … three challenges hinder the direct adoption of convolutional neural networks (CNNs) for HSI classification. First, typical HSIs contain hundreds of spectral channels that encode abundant pixel-wise spectral information, leading to the curse of dimensionality. Second, HSIs usually have relatively …

    waterloo Repository record for Spectral-Spatial Neural Networks and Probabilistic Graph Models for Hyperspectral Image Classification (opens in a new tab)

  8. Deep learning networks for automatic brain tumour segmentation from MRI data

    … global features directly from the input images. Transposed convolution was employed in up-sampling path. The proposed network was evaluated for the segmentation of five tumour regions: whole tumour (WT), tumour core(TC), necrotic and nonenhancing tumour (NCR/NET), edema (ED), and enhancing tumour …

    strathclyde Repository record for Deep learning networks for automatic brain tumour segmentation from MRI data (opens in a new tab)

  9. Neuro-general computing an acceleration-approximation approach

    … design and approximation in the domain of deep convolution neural networks. More specifically, this thesis explores utilizing the complementary specialization techniques of acceleration and approximation in the domain of deep convolutional neural networks. I propose a co-design hardware-software …

    gatech Repository record for Neuro-general computing an acceleration-approximation approach (opens in a new tab)