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 129 for “"Model generalization"”.
-
A Multifaceted Analysis of Model Generalization in Challenging Environments
Deep learning models have become central to modern artificial intelligence systems, achieving strong performance across a wide range of visual recognition and reasoning tasks. However, deploying these models reliably in real-world environments remains challenging. In practice, models often …
-
Enhancing Model Generalization in Weakly Supervised and Low-Shot Transfer Learning Scenarios
… an adversarial training technique that improves model resilience. Our contribution is an adversarial technique that suppresses all features in a DNNs output feature vector that are specific to a particular sample, while preserving the features that are useful to classifying the samples. This …
-
A model generalization study in localizing indoor cows with cow localization (colo) dataset
… task difficult, such as the scarcity of data for model fine-tuning and the inability to generalize models effectively. To address these challenges, we introduces COLO (COw LOcalization), a publicly available dataset comprising localization data for Jersey and Holstein cows under various lighting …
-
Improving Model Generalization of Pneumonia Detection from Chest Xray Images Using Deep Learning and Transfer Learning
… tool. Despite their promise, deep learning models for pneumonia detection often face limitations in generalization, performing strongly on familiar datasets but losing accuracy when applied to unseen data from different clinical environments. This study addresses that challenge by applying …
-
Predicting risk of readmission in heart failure patients using electronic health records
… of attention mechanism in readmission prediction model based on long short-term memory(LSTM) networks and investigate the interpretability it offers regarding the importance of critical time during the visit in readmission prediction. Second given that, generally dataset is curated by combining …
-
Modelling and Classification of Motor Imagery EEG for BCI
… classification in BCI from the perspectives of model generalization and adaptation. In the presence of causal relationships in EEG signals, a computational model has been constructed for discriminative learning of propagation and spatial patterns. Ensemble learning of spatial filters has been …
-
Development of a Hybrid Physics-Guided and Machine Learning Based Remote Sensing Framework for Surface Water Monitoring
… observations for surface water monitoring, but model performance and transferability are often limited by illumination-driven variability, confounding signals, weak target separability, and poor generalization across different water bodies. This thesis aims to strengthen satellite-based surface …
-
Deep learning-based polyp segmentation network with a dual encoder-decoder
… such as boundary pixel definitions, as well as model generalization and overfitting issues. PSNet provides state-of-the-art (SOTA) performance with respect to two major semantic segmentation performance metrics, mean intersection-over-union (mIoU) and mean Dice (mDice) on 5 major publicly …
-
BENCHMARKING AND ENHANCING GENERALIZATION IN MULTILINGUAL SPEECH EMOTION RECOGNITION
… progress with self-supervised learning models, SER systems often struggle with generalization across diverse languages and unseen data distributions, limiting their real-world applicability. This thesis addresses these challenges by first introducing a large-scale benchmark to evaluate …
-
A Robust Data-Driven Framework for Artificial Intelligent Systems
… concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI systems by focusing on two key aspects: data robustness and model robustness. Data robustness poses significant challenges, including data shift, …
-
Towards Accurate Cuffless Blood Pressure Estimation with Reduced Calibration Requirements
… estimation accuracy and trend tracking; existing models often fail to accurately track BP trends, which is crucial for long-term monitoring; poor model generalization to new subjects leads to performance degradation; personalization strategies are inefficient, typically requiring a large number of …
-
TOWARDS EFFICIENT AND GENERALIZABLE 3D HUMAN POSE ESTIMATION AND ITS APPLICATIONS
… motions and large pose deformation. To improve model efficiency, we propose a novel point-based representation for monocular multi-person body mesh estimation, which achieves real-time inference speed. Furthermore, we present an inference stage optimization pipeline, which helps improve model …
-
Robust Representation Learning Solutions for Wireless Sensing Applications
… state information (CSI) data, and (3) ensuring model generalization across different environments. The first part of the thesis addresses the limited computation power of edge devices by developing a Real-time Sensing and Compression Network (RSCNet). RSCNet is a cloud-based architecture …
-
Effective Learning on Non-Stationary Data Distribution
… could be gradually forgotten when adapting the model to a new domain. We first propose a more challenging and realistic meta-learning scenario named Sequential Domain Meta-Learning (SDML). The agent will sequentially meta-learn a sequence of domains without forgetting previous knowledge. We …
-
OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION
Despite advances in deep learning, most models assume that test data match the training distribution (ID). However, real-world data are unpredictable and often contain out-of-distribution (OOD) samples, posing significant challenges. This thesis focuses on data-efficient OOD learning to improve …
-
FEW-SHOT IMAGE RECOGNITION AND OBJECT DETECTION
… applications still faces challenges in model generalization and learning efficiency. Motivated by this, we study the problem of few-shot learning and its boarder applications in object detection, which are important for many real-world industrial applications. Our goal is to design …
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
Machine learning (ML) models often rely on spurious correlations in the training data, leading to performance degradation and unreliability when processing inputs under distribution shifts. This thesis systematically studies the robustness to distribution shifts for ML models from a data-centric …
-
STUDY OF BRAIN TUMOR PREDICTION BY USING MACHINE LEARNING
… experience project utilized the EfficientNetV2B3 model to predict brain tumors. The research questions are: (Q1) Does the study's deep learning model perform better than current methods when it comes to predicting brain tumor? (Q2) How much does the model's performance change when using different …
-
Machine Learning Techniques for Radio Propagation Modeling with Big Data
… with the industry-standard midband propagation model, P.1812. P.1812 is a path-specific path loss model that represents above-ground obstructions (clutter) using representative clutter heights derived from local information. This thesis implements a path-specific path loss prediction method that …
-
A study of integrating large-scale variety trial data and phenology-based hybrid modeling for cultivar-level soybean yield prediction
… predictive capacity of the DSSAT-CROPGRO-Soybean model and its integration with data-driven approaches. The first study introduces a yield-only calibration strategy that uses likelihood-based optimization and a large variety-trial dataset to estimate cultivar parameters without requiring …
Page 1 of 7