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 1215 for “"CNNs"”.

  1. Efficient Ultrasound Image Enhancement Using Lightweight CNNs

    Plane-wave ultrasound imaging allows for very high frame rates. During image reconstruction, conventional delay-and-sum beamforming can be replaced by the quicker Fourier-domain remapping method. Typically, after Fourier-domain reconstruction, postbeamforming interpolation is needed to increase the …

    uvic Repository record for Efficient Ultrasound Image Enhancement Using Lightweight CNNs (opens in a new tab)

  2. Reconfigurable Convolution Implementation for CNNs in FPGAs

    … processing. Convolutional Neural Networks (CNNs) in particular have outperformed every competitor in image classification benchmarks, but suffer from high computation and storage complexities. It is becoming more apparent to extend this breakthrough technology to embedded applications that …

    washington Repository record for Reconfigurable Convolution Implementation for CNNs in FPGAs (opens in a new tab)

  3. Models of Visual Attention in Deep Residual CNNs

    Feature reuse from earlier layers in neural network hierarchies has been shown to improve the quality of features at a later stage - a concept known as residual learning. In this thesis, we learn effective residual learning methodologies infused with attention mechanisms to observe their effect on …

    whiterose Download PDF for Models of Visual Attention in Deep Residual CNNs (opens in a new tab)

  4. Virtual Multimodal Object Detection and Classification with Deep CNNs

    In this thesis, first we present two powerful image enhancement methods, both originating from the domain of unlighting illumination normalization. Then, provided a gray-scale image database (physical image modality), we postulate that the images generated by any of the two image enhancement …

    houston Repository record for Virtual Multimodal Object Detection and Classification with Deep CNNs (opens in a new tab)

  5. Self-Supervised Cross-Connected CNNs for Binocular Disparity Estimation

    When developing autonomous vehicles, sensors with high accuracy and speed are needed. One type of sensor that can gather a lot of information is the camera. From two stereo images a disparity between them can be calculated, and from that the depth. The drawback with today’s algorithms is the …

    chalmers Repository record for Self-Supervised Cross-Connected CNNs for Binocular Disparity Estimation (opens in a new tab)

  6. Software-only computation reuse techniques for energy efficient CNNs

    … were put together to enable large-scale use of CNNs as we know today. Thus far, most of these achievements have been based on improving convolutions by chasing the parallel execution of MAC operations through the replication of floating-point units. However, these solutions fall far short of …

    brazil-ufrgs Repository record for Software-only computation reuse techniques for energy efficient CNNs (opens in a new tab)

  7. A Suitability Score to optimize CNNs on an FPGA accelerator

    … for deploying convolutional neural networks (CNNs) on field-programmable gate arrays (FPGAs), targeting high-throughput operation under constraints of computational resources and latency. The proposed approach integrates model-level restructuring, hardware-aware scheduling, and …

    soton Download PDF for A Suitability Score to optimize CNNs on an FPGA accelerator (opens in a new tab)

  8. USING CNNS TO UNDERSTAND LIGHTING WITHOUT REAL LABELED TRAINING DATA

    … vision, and deep Convolutional Neural Networks (CNNs) now dominate most of the problems in computer vision. Despite their success, deep CNNs are notorious for their data hungry nature compared with traditional learning based methods. While collecting images from the internet is easy and fast, …

    maryland Repository record for USING CNNS TO UNDERSTAND LIGHTING WITHOUT REAL LABELED TRAINING DATA (opens in a new tab)

  9. Pruning for Efficient Deep Learning: From CNNs to Generative Models

    … for the model, enabling designing efficient CNNs customized for their target application. Finally, we develop a framework for simultaneous pretraining and pruning of CNNs, which combines the first two stage of the pretrain-prune-finetune pipeline commonly used in model pruning and reduces its …

    maryland Repository record for Pruning for Efficient Deep Learning: From CNNs to Generative Models (opens in a new tab)

  10. Optimizing for adaptive CNNs on FPGAs : a multi-level approach

    … use case is the Convolutional Neural Networks (CNNs) used in many IoT applications. At the same time that it is possible to trade the CNN computational load for quality with algorithmic-level optimizations like quantization, pruning, and early-exit, it is also possible to optimize the hardware …

    brazil-ufrgs Repository record for Optimizing for adaptive CNNs on FPGAs : a multi-level approach (opens in a new tab)

  11. Comparative Analysis of Vision Transformers and CNNs in Melanoma Classification

    … (ViT) and Convolutional Neural Networks (CNNs) for melanoma cancer detection. This study further examines the influence of domain-specific transfer learning on improving melanoma detection accuracy by pre-training these deep learning models on various datasets, such as ImageNet, BreakHis, …

    concordia Download PDF for Comparative Analysis of Vision Transformers and CNNs in Melanoma Classification (opens in a new tab)

  12. Understanding Deep Representations in CNNs from Concepts to Relations to Rules

    … we focus on Convolutional Neural Networks (CNNs) for image classification tasks and have leveraged our approach to make assumptions about what semantic concepts and relations are effectively learned and hidden in deep representations for computer vision models. Our results demonstrate the …

    dcu Download PDF for Understanding Deep Representations in CNNs from Concepts to Relations to Rules (opens in a new tab)

  13. Speech Mode Classification using the Fusion of CNNs and LSTM Networks

    Speech mode classification is an area that has not been as widely explored in the field of sound classification as others such as environmental sounds, music genre, and speaker identification. But what is speech mode? While mode is defined as the way or the manner in which something occurs or is …

    wvu Repository record for Speech Mode Classification using the Fusion of CNNs and LSTM Networks (opens in a new tab)

Page 1 of 61