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"”.
-
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 …
-
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 …
-
Causal Graphical Models in AI Reasoning & Expert Decision-Making
… causal world models, using program synthesis and test-time training.
-
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 …
-
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 …
-
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
-
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.
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …