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 “"Segment-Anything-Model"”.

  1. SAMPLS: A prompt engineering approach using Segment-Anything-Model for PLant Science research

    … called PlantSeg utilized U-Net for cell wall segmentation. U-Net is a neural network model that requires training with a large amount of manually labeled confocal images and lacks generalizability. In this research, we test a foundation model called the Segment Anything Model (SAM) to evaluate …

    vt Repository record for SAMPLS: A prompt engineering approach using Segment-Anything-Model for PLant Science research (opens in a new tab)

  2. Comparación de algoritmos de segmentación heurística de imágenes de angiografía coronaria utilizando técnicas no supervisadas

    El presente trabajo aborda el problema de la segmentación no supervisada de vasos coronarios en imágenes de angiografía, un desafío debido al ruido, los artefactos y la complejidad de las estructuras vasculares. Se comparan dos enfoques de segmentación, W-Net y Segment Anything Model (SAM), y se …

    rosario Repository record for Comparación de algoritmos de segmentación heurística de imágenes de angiografía coronaria utilizando técnicas no supervisadas (opens in a new tab)

  3. Last-Meter Delivery: Solving the Unattended Delivery Challenge from Streets to Doorsteps

    … a methodology for implementing Large Language Model (LLM), and Vision Language Model (VLM) to enable delivery robots to identify the final delivery target and navigate the complex terrain from the curb to the front door. The proposed solution aims to enhance the autonomy and safety of last-mile …

    mit Repository record for Last-Meter Delivery: Solving the Unattended Delivery Challenge from Streets to Doorsteps (opens in a new tab)

  4. AI-Driven Pig Monitoring System: Behavior and Weight Analysis

    … we develop an automated pipeline using the Segment Anything Model (SAM) with deep learning, where our Xception-Net architecture achieves a mean absolute percentage error of 7.42%. For weight forecasting, we propose multi-input deep learning architectures combining spatial and temporal …

    vt Repository record for AI-Driven Pig Monitoring System: Behavior and Weight Analysis (opens in a new tab)

  5. Uncertainty-aware fusion of foundation and task-specific models for cardiac MRI segmentation

    Vision foundation models, such as the Segment Anything Model (SAM), demonstrate strong zero-shot generalization but lack precision with anatomically challenging structures. In contrast, convolutional neural network (CNN)-based models achieve high accuracy on domain-specific data but struggle to …

    uoit Repository record for Uncertainty-aware fusion of foundation and task-specific models for cardiac MRI segmentation (opens in a new tab)

  6. Efficient Segment Anything on the Edge

    The Segment-Anything Model (SAM) is a vision foundation model facilitating promptable and zero-shot image segmentation. SAM-based models have a wide range of applications including autonomous driving, medical image segmentation, VR, and data annotation. However, SAM models are highly …

    mit Repository record for Efficient Segment Anything on the Edge (opens in a new tab)

  7. Design and Integration of Machine Learning-Based Vision System for Automated Power Line Inspection Using a Mobile Damping Robot

    … using traditional supervised machine learning models, including Random Forest, Multi-Layer Perceptron, and Gradient Boosting. Next, the second method provides a more detailed assessment by classifying conductors into four categories: Healthy, Minor Corrosion, Pollution-Induced Corrosion, and …

    vt Repository record for Design and Integration of Machine Learning-Based Vision System for Automated Power Line Inspection Using a Mobile Damping Robot (opens in a new tab)

  8. Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains

    … random sampling. For data synthesis, generative models face their own set of challenges. Despite their promise for synthetic data generation, these models frequently lack mechanisms to disentangle generative factors at the representation level, limiting their controllability. Additionally, …

    passau-thes Repository record for Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains (opens in a new tab)

  9. Leveraging Autonomous Vehicles In Transportation Asset Management

    … connects traffic sign detection with sign-region segmentation and combines monocular depth evidence with GPS-and-bearing coordinate projection so that duplicate-filtered traffic sign inventory records can be obtained. A case study using annotated road sign imagery and vehicle-mounted roadway video …

    houston Repository record for Leveraging Autonomous Vehicles In Transportation Asset Management (opens in a new tab)