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 55 for “"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 …
-
Improving Flexibility and Performance in Metric-Based Few-Shot Classification
… These concerns have fueled interest in few-shot classification, or the ability to classify novel object types using very few (only one to five) reference images per class. Performance on few-shot classification benchmarks has since seen steady improvement and the field remains a healthy area …
-
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
… 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 …
-
Advancing space-borne computational vision for rare object mapping
… rare targets. The first part focuses on the classification and precise localization of rare targets like Maasai Boma homesteads across broad geographic areas. A mapping workflow is developed using a Proxyless-NAS deep convolutional neural network (DCNN) for broad-area scanning and a two-phase …
-
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 …
-
Spatial-Temporal change detection in satellite imaging-monitoring /
… 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 …
-
G2G - From Data Generation to Model Generalisation
… generating synthetic examples to support few shot classification; extracting structure from unlabelled inputs through self supervised objectives; and creating artificial patterns to guide visual reidentification of animals in ecological monitoring. A key contribution of this thesis is to show …
-
Distributional robustness: towards challenging and real-world settings of distribution shift
… 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, typical …
-
Uncertainty-Aware Meta-Learning for Learning from Limited Data
… the two most popular limited data problems: few-shot regression and few-shot classification. For both problems, the developed models need to be robust, and output well-calibrated trustworthy predictions while remaining computationally cheap and label-efficient to ensure real-world applicability. …
-
Generative AI for Digital Pathology: Advancing Diffusion, Vision-Language, and Safety-Aware Models
… 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, …
-
Malware Detection and Behavioral Analysis in IoT Environments: A Multi-Study Deep Learning Approach
… labeled example, reached 87.6% accuracy at one-shot, and outperformed standard baselines through fifty-shot. Classification used a state-space sequence model that captures relationships between features a flat vector misses, and reached an 89% macroF1-score on structurally similar ransomware …
-
One-shot Learning In Deep Sequential Generative Models
… advancements, the challenging domain of one-shot learning still persists. While the human brain is capable of learning a new visual concept with ease, sometimes even at a glance, Deep Learning-based techniques show serious drawbacks in handling problems with small datasets. Much of the …
-
Video analysis and indexing in compressed domain
… have developed a unified framework for semantic shot classification in sports videos featured higher structured constraints. With correctly classified sports video shots, further structural and temporal analysis, such as event detection, video skimming, table of content, etc., will be greatly …
-
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 its …
-
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 …
-
Fine-Tuning CLIP for Security Object Classification and Detection in X-ray Images
… driven major advances, particularly in object classification and detection. However, the diversity of threat objects and the limited availability of high-quality labeled X-ray data pose persistent challenges for conventional detectors. Emerging vision–language models, such as CLIP, provide a …
-
Representative-based Big Data Processing in Communications and Machine Learning
… (GANs), graph-based label propagation, few shot classification, and fast subspace clustering.
-
Advancing Generalization in Deep Representation Learning
… 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 …
Page 1 of 3