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 86 for “"vision-language model"”.
-
Vision Language Model Guided Zero-shot Classification
Among various core tasks in Computer Vision, 2D image and 3D object classification are fundamental tasks which serve as the foundation for numerous applications including scene understanding, robotics and autonomous navigation. Vision Language Model (VLMs) are deep learning architectures designed …
-
Large Vision Language Model Driven Differential Profiling of Brain Spatial Proteomics Data
… on cell segmentation or classification and often model cells and protein channels independently, while large language models cannot directly interpret and differentially profile whole-slice brain images. We propose a data-driven framework that integrates multichannel molecular signals, spatial …
-
A Vision-Language Model Framework for Geographically And Environmentally Informed Soundscape Assessment
… spatial scalability. This study explores whether Vision-Language Models (VLMs) can infer acoustic conditions directly from street-view imagery, offering a scalable alternative to dense sensor networks. This thesis focuses on three tasks: (1) identifying visible sound sources (vehicles, …
-
Enhancing Infrastructure Monitoring with Calibrated Vision Language Model Ensembles: A Graffiti Detection Case Study
… and (3) damage assessment using a specialized Vision Language Model (VLM) ensemble. Our ensemble approach employs probability calibration and weight optimization, outperforming individual models with an 84.4% F1 score. To address extreme data scarcity, we developed a synthetic graffiti …
-
Vision Language Model Based Systems for Optical Character Recognition of Historical Swedish Newspaper Material
… whether small to medium-sized open-source Vision Language Models are competitive for Optical Character Recognition compared to traditional models. It is found that a fine-tuned Qwen3-VL-8B-Instruct in combination with a simple repetition trimmer is able to outperform the traditional OCR …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving
… a convolutional neural network (CNN) and a vision language model (VLM) for autonomous driving, with the CNN acting as a preliminary control signal predictor and the VLM acting as a final predictor, correcting or confirming control signals the CNN predicts. We train a CNN from scratch and …
-
A hybrid deep learning and vision-language model framework for automated information extraction from legacy construction drawings
… (OCR), and a fine-tuned Qwen3-VL-8B-Instruct vision-language model (VLM). Detected elements are organized using spatial relationships and task-specific rules to establish component records and associate relevant attributes. Localized image regions, reconstructed dimension lines, and …
-
A Two Stage Florence-Zephyr Vision Language Model for Pulmonary Nodule Characterization and Clinical Decision Making for Lung CT
… This thesis presents the Florence-Zephyr Vision Language Model (FZ-VLM), a two-stage framework for pulmonary nodule characterization and clinical decision making. A fine-tuned Florence-2 model extracts radiological attributes from expert-annotated CT slices, while Zephyr-7B generates …
-
Regos-kalbos modelių adaptavimo metodų tyrimas dirbant su lietuviškais duomenimis /
This paper analyses the adaptation of vision-language models for the Lithuanian language. Since most vision-language models are trained and evaluated with English data, there is limited information about their ability to generate image descriptions in Lithuanian. This paper compares open-weight …
-
A Submodular Approach to Find Interpretable Directions in Text-to-Image Models
Text-to-image models have significantly improved the field of image editing. However, finding attributes that the model can actually edit is still a remaining challenge. This thesis proposes a solution to this problem by leveraging a multimodal vision-language model (MMVLM) to find a list of …
-
Exploring Image-to-Text Visual Search Using Open Source Models
… which utilizes image descriptions generated by vision-language models instead of image features, where the descriptions are converted into embeddings in order to match with other search entries. Evaluation data indicate that the method can provide satisfactory retrieval performance in addition …
-
DYNAMIC NEURAL NETWORKS FOR EFFICIENT VISION MODEL INFERENCE
… and 1.7× speedup with improved quality. Vision-Language Model (VLM) Acceleration: By implementing a dynamic small-large model cooperation mechanism, we achieve up to 3× faster inference while maintaining competitive performance. In conclusion, this research provides a comprehensive …
-
Connecting Text and Charts Using Large Vision-Language Models
… documents. In this thesis, we propose two large vision-language model (LVLM)-based frameworks—a single-agent baseline and a multi-agent architecture—for automatically linking textual descriptions with their corresponding chart data. Both frameworks extract structured data from chart images and …
-
VISION-BASED DEEP REINFORCEMENT LEARNING FOR ROBOTIC MANIPULATION
… argues that the main limiting factor in vision-based deep reinforcement learning (DRL) for robotic manipulation is the data provided to the learner rather than the learning algorithm. Three data channels are examined: perception, initialization, and supervision. First, a compact …
-
Autonomous Deficiency Detection and Vision-Language Summarization for Underground Infrastructure on Embedded Edge Systems
… detection, geometric assessment, and natural language reporting on resource- constrained edge computing platforms. Three core components address this challenge. First, RAPID-SCAN, a novel semantic segmentation architecture utilizing a Dynamic Feature Pyramid Network and Channel-Spatial …
Page 1 of 5