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 30 for “"Zero-shot classification"”.
-
Vision Language Model Guided Zero-shot Classification
… 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 to process and …
-
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
… that redefines optimal transport in the realm of zero-shot classification. Conventional methods often suffer from miscalibration and a lack of adaptability, as they rely on fixed cost matrices derived solely from pre-trained model embeddings. In contrast, GeoTTER addresses these limitations by …
-
Spatial-Temporal change detection in satellite imaging-monitoring /
… and the second experiment employs CLIP-based zero-shot classification to effectively detect changes without the need for extensive labeling. Additionally, caption based change classification done which these captions generated using Llama model. The work further investigates the use of the …
-
Distributional robustness: towards challenging and real-world settings of distribution shift
… at foundation vision-language models for the zero-shot classification problem, and the challenges of adapting such models from the pre-trained data distribution to a downstream distribution. While vision-language models have gained popularity as a solution for the classification problem, …
-
Generative AI for Digital Pathology: Advancing Diffusion, Vision-Language, and Safety-Aware Models
… image-caption datasets and the sensitivity of zero-shot classification to prompt design. To address these challenges, language rewrites generated by a large language model (LLM) are used to enrich an existing dataset, resulting in substantial performance gains. Additionally, a novel context …
-
Multimodal Representation Learning in Medical Using Vision-Language Models
… extraction and summarization, and modality-aware classification. Using OPEN-PMC-2M, we conduct controlled experiments to quantify the effect of each processing step on contrastive pretraining. Our findings show that subfigure decomposition and enriched captions substantially improve retrieval, …
-
Optimizing Real-time Traffic Sign Recognition Algorithms For Mobile Devices.
… systems by focusing on the Detection and Classification modules to accurately recognize a broader range of traffic signs. A novel pipeline leveraging CLIP architecture is proposed, featuring prompt-based classification. An optimized YOLO (You Only Look Once) detection model with an …
-
Hybrid ConVIRT - enhancing medical image-text representation learning of vision language models
… Mix, and CheXpert) using linear probe and zero-shot classification demonstrates Hybrid-ConVIRT’s enhanced discriminative power and feature robustness, particularly on COVID and CheXpert datasets. Although MedCLIP shows a slight advantage on the Tuberculosis dataset, this is likely due to …
-
Enriching vision representation by deep neural networks and self-supervised learning
… extraction layer. It achieves competitive image classification accuracy with significantly decreased model parameters. Another attempt at efficient deep learning is a proposed channel pruning approach that compresses deep neural networks by identifying and removing redundant channels using …
-
Advancing Generalization in Deep Representation Learning
… significantly enhances fairness and accuracy in zero-shot classification tasks, surpassing existing debiasing techniques. Together, the methodologies and theoretical insights developed in this thesis substantially advance our understanding and practical approaches to improving generalization at …
-
Towards Autonomous Histopathological Diagnosis: An End-to-End Multi-Agent AI Framework for Diagnostic Decision-Making and Interpretation
… that achieves state-of-the-art performance in zero-shot classification and cross-modal retrieval tasks. Building on this foundation, we developed Quilt-Instruct to create Quilt-LLaVA, a large language and vision assistant specifically tailored for histopathology. Quilt-LLaVA can analyze WSI …
-
Learning to Build Probabilistic Models with Limited Data
… challenging tasks in this regime including few-shot learning, zero-shot learning, and structured prediction. In the first part of this thesis, we propose a deep metric learning approach to few-shot and zero-shot classification that generalizes from just a few examples. It does so by exploiting a …
-
Optimizing Large Language Models and Multimodal Approaches for Biomedical Publication and Satellite Imagery
… include the development of a custom dataset for classification and Question and Answering (Q&A) tasks, fine-tuning Transformer models like the Bidirectional Encoder Representations from Transformers (BERT) and addressing multi-span answer issues with the TAg-based Span Extraction (TASE) model. …
-
Investigating the Impacts of Policy Stringency on the Public Perceptions of Pandemic Policies, Sentiment Analysis of Tweets During the Second and Third COVID-19 Pandemic Waves in Ontario
… users in Ontario were compiled and sorted using zero-shot classification into subgroups for relevant categories – vaccine mandates, mask policies, and lockdown measures. These tweets were then analyzed using sentiment analysis and the COVID-19 Stringency Index to identify trends in the sentiments …
-
Identifying Online Conspiracy Theories: A Multiphase Analysis of AI Models
… Transformer models (BERT, BERTweet); and (3) zero-shot classification with Large Language Models (LLMs). The results reveal a clear hierarchy of performance, with LLMs demonstrating superior accuracy, achieving a top F1-score of 0.880. Notably, a hybrid approach combining Google’s foundation …
-
Automated Theme Extraction from Homeless Shelter Case Notes: A Comparative Evaluation of Machine Learning and Large Language Model Methods
… learning baselines, as well as transformer-based zero-shot classification, and prompt engineering and fine-tuning of smaller open-source language models. A manually annotated subset of case notes from the Calgary Drop-In Centre served as the basis for method development and evaluation. Based on …
-
The Comparison of Human and Machine Performance in Object Recognition
… scenarios without fine-tuning or task-specific zero-shot classification. While fine-tuning can significantly enhance machine performance in constrained tasks, this advantage may overestimate machine capabilities relative to humans. In Chapter 3, I test the assumption that human performance …
-
ENHANCING NLP CAPABILITIES: STRATEGIES FOR LANGUAGE MODEL ADAPTATION IN LOW-RESOURCE TEXT CLASSIFICATION TASK AND EVALUATIONS
Nowadays, there are two approaches solving classification tasks in Natural Language Processing (NLP). The traditional way usually includes the adaptation of smaller Pre-trained Large Language Models (BERT, RoBERTa, etc.) to specific downstream tasks that offer both remarkable opportunities and …
-
Deep Unsupervised Learning for Biodiversity Analyses: Representation learning and clustering of bacterial, mitochondrial, and barcode DNA sequences
… alignment-free methods in taxonomic classification. Motivated by this success, this dissertation investigates the potential of unsupervised learning-based alignment-free algorithms in genomic signature categorization. We conclude that meaningful information can be learned without …
-
Label Shift Problem for Image Classification Tasks -- A Comprehensive Analysis
… type of distribution shift that happens in classification tasks, where the source domain (train set) and target domain (test set) have different label distributions p(y) but identical distributions of image given label p(x|y). Under label shift, the classifier trained on the source domain …
Page 1 of 2