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 14 of 14 for “"test-time training"”.

  1. Test-Time Training for Image Inpainting

    … and coherent content. The usual process involves training a CNN on a large collection of examples that it can learn from, to later apply this knowledge on new, unseen images with areas to complete. One important consideration is that each training dataset has its own domain, and domains in the …

    waterloo Repository record for Test-Time Training for Image Inpainting (opens in a new tab)

  2. Domain Generalization and its Application in Deepfake Detection

    … when there is a distribution shift between the training and test environments. This thesis aims to ease the generalization problem from both the general machine learning and specific downstream application perspectives. For general machine learning systems, we propose two effective domain …

    adelaide Repository record for Domain Generalization and its Application in Deepfake Detection (opens in a new tab)

  3. Causal Graphical Models in AI Reasoning & Expert Decision-Making

    … causal world models, using program synthesis and test-time training.

    cornell Repository record for Causal Graphical Models in AI Reasoning & Expert Decision-Making (opens in a new tab)

  4. Model Optimization for Federated Learning and Flow-Based Image Restoration

    … modules for efficient feature aggregation, test-time training for adaptation to unseen degradations, and a truncated flow matching prior to enforce structural consistency. MoiréXNet achieves state-of-the-art performance across several real-world benchmarks. The third chapter addresses the …

    mcmaster Repository record for Model Optimization for Federated Learning and Flow-Based Image Restoration (opens in a new tab)

  5. Auxiliary llearning for patch and WSI pathology image classification

    … model robustness at the patch level by combining Test-Time Training (TTT) with Model-Agnostic Meta-Learning (MAML). This bi-level optimization strategy leverages MAML to train a model for rapid adaptation, while TTT dynamically fine-tunes its parameters during inference, allowing for effective …

    concordia Download PDF for Auxiliary llearning for patch and WSI pathology image classification (opens in a new tab)

  6. Improving problem-solving capabilities of language model: data, architecture and algorithms

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01

    uiuc Repository record for Improving problem-solving capabilities of language model: data, architecture and algorithms (opens in a new tab)

  7. Improving the Robustness of Deep Learning Based Image Reconstruction Models Against Natural Distribution Shifts

    … sensing that relies on self-supervision during training paired with test-time training at inference. We show that for four natural distribution shifts, this method essentially closes the distribution shift performance gap for state-of-the-art architectures for accelerated MRI.

    rice Repository record for Improving the Robustness of Deep Learning Based Image Reconstruction Models Against Natural Distribution Shifts (opens in a new tab)

  8. Robust and generalizable deep geometric representation learning for 3D point clouds

    … on labeled datasets, which are costly and time-consuming to acquire. This motivates the development of self-supervised learning methods that can pretrain models on unlabeled data and learn transferable geometric representations for downstream tasks with limited annotations. Second, models …

    ets-quebec Download PDF for Robust and generalizable deep geometric representation learning for 3D point clouds (opens in a new tab)

  9. Advancing Machine Learning for Resilient and Safe Critical Systems: From Theory to Applications

    … validation. We first study the problem of training neural networks that certifiably satisfy prescribed input-output specifications, such as reachability and Lipschitz robustness, by representing activation nonlinearities and specifications through quadratic constraints and applying a loop …

    vt Repository record for Advancing Machine Learning for Resilient and Safe Critical Systems: From Theory to Applications (opens in a new tab)

  10. Steps Toward Open-ended Reasoning and Discovery with Language Models

    … capabilities because tasks are contaminated by training data. To address this, we introduce LLM-SRBench, a multi-domain benchmark designed with synthetic novel components to test models beyond memorization in the task of scientific model discovery. Results on LLM-SRBench show significant …

    vt Repository record for Steps Toward Open-ended Reasoning and Discovery with Language Models (opens in a new tab)

  11. MITIGATING DATA SCARCITY CHALLENGES IN MEDICAL IMAGING ANALYSIS:ADVANCED LEARNING APPROACHES WITH EMPHASIS ON HEMOPHILIC ULTRASOUND IMAGES

    … (CAD) systems. However, the lack of labeled training data makes the effective utilization of DL techniques in the medical domain impractical, leading to suboptimal performance in various imaging tasks, such as classification, detection, and segmentation. This thesis investigates the …

    milano Repository record for MITIGATING DATA SCARCITY CHALLENGES IN MEDICAL IMAGING ANALYSIS:ADVANCED LEARNING APPROACHES WITH EMPHASIS ON HEMOPHILIC ULTRASOUND IMAGES (opens in a new tab)

  12. Deep Learning Approaches to Low-level Vision Problems

    … methods address the low-level vision problem by training a neural network to approximate the mapping from the inputs to the desired ground truths. However, directly learning this mapping is usually difficult and cannot achieve ideal performance. Besides, under the setting of unsupervised …

    mcmaster Repository record for Deep Learning Approaches to Low-level Vision Problems (opens in a new tab)

  13. Learning to Learn Sequential Dynamics: Context-Aware Out-of-Distribution Adaptation for Time Series and Physical Systems

    … to tackle problems beyond the forecasting of time-dependent physical systems. The third contribution introduces a new problem of generalisation across system hierarchies, demonstrating both the effectiveness and limitations of mixtures of experts as potential foundation models. A final …

    bristol Repository record for Learning to Learn Sequential Dynamics: Context-Aware Out-of-Distribution Adaptation for Time Series and Physical Systems (opens in a new tab) Download PDF for Learning to Learn Sequential Dynamics: Context-Aware Out-of-Distribution Adaptation for Time Series and Physical Systems (opens in a new tab)

  14. Computer vision methods adapting to new domains with few samples

    … the assumption that the data encountered at test time will be drawn from the same distribution as the training set. In real-world scenarios, this assumption rarely holds. Even subtle variations in lighting, camera properties, background textures, or object appearances can lead to significant …

    ets-quebec Download PDF for Computer vision methods adapting to new domains with few samples (opens in a new tab)