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"”.
-
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 …
-
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
-
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 …
-
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
-
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 …
-
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
-
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 …
-
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
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
Page 1 of 3