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"”.

  1. 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 …

    anu Repository record for A Multifaceted Analysis of Model Generalization in Challenging Environments (opens in a new tab)

  2. 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 …

    adelaide Repository record for Enhancing Model Generalization in Weakly Supervised and Low-Shot Transfer Learning Scenarios (opens in a new tab)

  3. 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 …

    vt Repository record for A model generalization study in localizing indoor cows with cow localization (colo) dataset (opens in a new tab)

  4. 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 …

    uwtsd Repository record for Improving Model Generalization of Pneumonia Detection from Chest Xray Images Using Deep Learning and Transfer Learning (opens in a new tab) Download PDF for Improving Model Generalization of Pneumonia Detection from Chest Xray Images Using Deep Learning and Transfer Learning (opens in a new tab)

  5. 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 …

    rit Repository record for Predicting risk of readmission in heart failure patients using electronic health records (opens in a new tab)

  6. 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 …

    nus Repository record for Modelling and Classification of Motor Imagery EEG for BCI (opens in a new tab) Download file for Modelling and Classification of Motor Imagery EEG for BCI (opens in a new tab)

  7. 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 …

    concordia Download PDF for Development of a Hybrid Physics-Guided and Machine Learning Based Remote Sensing Framework for Surface Water Monitoring (opens in a new tab)

  8. 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 …

    manitoba Repository record for Deep learning-based polyp segmentation network with a dual encoder-decoder (opens in a new tab)

  9. 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 …

    vcu Repository record for BENCHMARKING AND ENHANCING GENERALIZATION IN MULTILINGUAL SPEECH EMOTION RECOGNITION (opens in a new tab)

  10. 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, …

    usf Repository record for A Robust Data-Driven Framework for Artificial Intelligent Systems (opens in a new tab)

  11. 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 …

    ottawa-retro Repository record for Towards Accurate Cuffless Blood Pressure Estimation with Reduced Calibration Requirements (opens in a new tab)

  12. 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 …

    nus Repository record for TOWARDS EFFICIENT AND GENERALIZABLE 3D HUMAN POSE ESTIMATION AND ITS APPLICATIONS (opens in a new tab) Download file for TOWARDS EFFICIENT AND GENERALIZABLE 3D HUMAN POSE ESTIMATION AND ITS APPLICATIONS (opens in a new tab)

  13. 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 …

    york Repository record for Robust Representation Learning Solutions for Wireless Sensing Applications (opens in a new tab)

  14. 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 …

    buffalo Repository record for Effective Learning on Non-Stationary Data Distribution (opens in a new tab)

  15. 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 …

    nus Repository record for OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION (opens in a new tab) Download file for OUT-OF-DISTRIBUTION LEARNING FOR ROBUST VISION PERCEPTION (opens in a new tab)

  16. 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 …

    nus Repository record for FEW-SHOT IMAGE RECOGNITION AND OBJECT DETECTION (opens in a new tab) Download file for FEW-SHOT IMAGE RECOGNITION AND OBJECT DETECTION (opens in a new tab)

  17. 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 …

    nus Repository record for TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE (opens in a new tab) Download file for TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE (opens in a new tab)

  18. 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 …

    csusb Repository record for STUDY OF BRAIN TUMOR PREDICTION BY USING MACHINE LEARNING (opens in a new tab)

  19. 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 …

    carleton Repository record for Machine Learning Techniques for Radio Propagation Modeling with Big Data (opens in a new tab)

  20. 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 …

    missouri Repository record for A study of integrating large-scale variety trial data and phenology-based hybrid modeling for cultivar-level soybean yield prediction (opens in a new tab)

Page 1 of 7