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 56 for “"Vision Models"”.

  1. Learning Reconfigurable Vision Models

    … in a wide variety of fields, such as computer vision, natural language processing, and speech recognition. However, these models have also been notorious for their high computational costs and substantial data requirements. Furthermore, they often present significant challenges to non-technical …

    mit Repository record for Learning Reconfigurable Vision Models (opens in a new tab)

  2. Sparse representation in deep vision models

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01

    uiuc Repository record for Sparse representation in deep vision models (opens in a new tab)

  3. Lifting 2D Vision Models into Structured Scene Representations

    … ineffective. Recent advances in 2D foundation models exhibit remarkable performance and generalization. Concurrently, several works have demonstrated lifting feature maps produced by these models into a 3D feature representation. This thesis further explores how lifting can be effectively …

    mit Repository record for Lifting 2D Vision Models into Structured Scene Representations (opens in a new tab)

  4. Methods for generating visual programs with optimizable vision models

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Methods for generating visual programs with optimizable vision models (opens in a new tab)

  5. Lightweight edge AI vision models for IoT-based insect monitoring

    … management. Unlike typical segmentation models designed for high-resource platforms, SemiY-Net introduces a design that deliberately reduces spatial resolution specifically at the output, trading off accuracy in favor of deployment feasibility. The model was trained and validated on a …

    cork Repository record for Lightweight edge AI vision models for IoT-based insect monitoring (opens in a new tab)

  6. Methods to improve quality and diversity of language-vision models

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01

    uiuc Repository record for Methods to improve quality and diversity of language-vision models (opens in a new tab)

  7. From local explanations to comprehensive mechanistic understanding of deep vision models

    Deep learning models have evolved into a cornerstone of modern industry and science, enabling applications from medical diagnosis and perception to conversational systems. Over the past two decades, both models and datasets have grown substantially in scale: models now reach trillions of …

    tu-berlin Repository record for From local explanations to comprehensive mechanistic understanding of deep vision models (opens in a new tab)

  8. Resource-efficient optimizations of 3D vision models for segmentation and detection

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01

    uiuc Repository record for Resource-efficient optimizations of 3D vision models for segmentation and detection (opens in a new tab)

  9. An unmanned aerial vehicle-based assessment method for quantifying computer vision models

    Computer vision is a growing field in computer science. Since the advancement of Machine learning, Computer vision solutions have been trending. As a result of the growing number of solutions and performance increases in Machine learning, machine learning solutions are now being utilized in the …

    uoit Repository record for An unmanned aerial vehicle-based assessment method for quantifying computer vision models (opens in a new tab)

  10. Understanding the Robustness of Vision Models and Humans to Occlusion-Based Corruptions

    … blocked from view (i.e., occluded). Moreover, vision models have made substantial progress in object recognition over the past decade. However, their proficiency in identifying occluded objects has not been thoroughly investigated. In this work, we analyze the robustness of models and humans to …

    mit Repository record for Understanding the Robustness of Vision Models and Humans to Occlusion-Based Corruptions (opens in a new tab)

  11. Attacking Computer Vision Models Using Occlusion Analysis to Create Physically Robust Adversarial Images

    … Thanks to recent developments in computer vision, specifically convolutional neural networks, autonomous vehicles have developed the ability to see at or above human-level capabilities, which in turn has allowed for rapid advances in self-driving cars. Unfortunately, much like humans being …

    calpoly Repository record for Attacking Computer Vision Models Using Occlusion Analysis to Create Physically Robust Adversarial Images (opens in a new tab)

  12. FORECASTING WINTER ROAD CONDITIONS: A DATA-DRIVEN APPROACH

    … we developed machine learning and computer vision models for predicting road surface temperatures and conditions using historical meteorological and road surface sensor data and images. We implemented machine learning algorithms to build models that can predict road surface temperatures and …

    cornell Repository record for FORECASTING WINTER ROAD CONDITIONS: A DATA-DRIVEN APPROACH (opens in a new tab)

  13. COMPOSITIONAL OBJECT-CENTRIC REPRESENTATIONS FOR ROBUST VISUAL PERCEPTION

    … advancements, real-world deployment of modern vision models in critical applications remains limited by poor out-of-distribution generalization, failures under occlusion, reliance on large high-quality datasets, and limited interpretability. We posit that these limitations arise from …

    nus Repository record for COMPOSITIONAL OBJECT-CENTRIC REPRESENTATIONS FOR ROBUST VISUAL PERCEPTION (opens in a new tab)

  14. Deep learning models for the perception of human social interactions

    … social interactions. In comparison, other vision problems, such as object recognition tasks, have been studied extensively and seen success by comparing state of the art computer vision models to neuroimaging data. In this thesis, I employ a similar method in order to study social …

    mit Repository record for Deep learning models for the perception of human social interactions (opens in a new tab)

  15. Harnessing Synthetic Data for Robust and Reliable Vision

    Progress in computer vision has been driven by models trained on large amounts of exemplar data for different tasks. These exemplar data sources intend to capture task-specific information and instance-level variations that a trained model will likely encounter in the wild. However, for conditions …

    gatech Repository record for Harnessing Synthetic Data for Robust and Reliable Vision (opens in a new tab)

  16. Next generation tools for smart electron microscopy

    … of high-resolution rescanning, cutting-edge vision models, incorporation of 3D information and vision transformers for improved neuronal segmentation and pipeline speedup. Our goal is to develop tools that improve the existing SmartEM pipeline, making it more versatile and effective for …

    mit Repository record for Next generation tools for smart electron microscopy (opens in a new tab)

  17. Learning by Watching and Learning by Doing

    … with it. Can we use these same signals to train vision models? In this thesis, we outline several works which use these paradigms as a basis for learning algorithms. First, we explore learning by watching in which video data is directly used to learn about the visual world. Second, we tackle …

    washington Repository record for Learning by Watching and Learning by Doing (opens in a new tab)

  18. Understanding Human Perception Through MooneyFaces

    Human vision is remarkably tolerant to image distortions: even when every pixel in an image has been destructively altered, as in classic Mooney displays, humans can still extract information about identity, pose, and more. Most current deep learning computer vision models perform well with …

    mit Repository record for Understanding Human Perception Through MooneyFaces (opens in a new tab)

  19. Soccer Last Touch and Automatic Event Detection with Skeletal Tracking Data

    … be limited in accuracy in practice. New computer vision models have enabled the extraction of player joint data from video broadcast, providing a newer, richer dataset for automatic event detection. The proposed thesis will seek to validate brand-new skeletal joint data, determine the last player …

    mit Repository record for Soccer Last Touch and Automatic Event Detection with Skeletal Tracking Data (opens in a new tab)

  20. Specialization of Vision Representations with Personalized Synthetic Data

    Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data to general-purpose representation learning, while advances …

    mit Repository record for Specialization of Vision Representations with Personalized Synthetic Data (opens in a new tab)

Page 1 of 3