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 8 of 8 for “"Domain Gaps"”.
-
Learning Sim-to-Real Robot Parkour from RGB Images
… challenges in sim-to-real transfer due to large domain gaps. This work proposes a novel approach for training an RGB parkour policy and demonstrates that it achieves performance comparable to depth-based approaches in simulation. Furthermore, we successfully deploy and evaluate our RGB policy on …
-
Low-cost Agents with Language Perception and Dynamic Inference
… data but also serves as a bridge to minimize domain gaps between different environments. However, transformer-based agents are burdened with high inference costs, especially when handling long-horizon visual content. To mitigate this, we introduce two strategies: (1) reducing visual input …
-
Opportunities for System Dynamics Research in Operations Management for Public Policy
… identify several overarching methodological and domain gaps for future research. Finally, we propose a process for using system dynamics with traditional operations management methodologies.
-
Essays in System Dynamics for Operations Management: Policy, Platforms and Pricing
… identify several overarching methodological and domain gaps for future research. Finally, we propose a process for using SD with traditional OM methodologies. Chapter 2 is joint work with Geoffrey Parker and Edward Anderson. We develop the Value Creation Lens, a framework, grounded in theory, for …
-
Leveraging Geometric Priors for In-the-wild Pose Estimation and 3D Reconstruction
… underlying priors, they often suffer from domain gaps and require large labeled datasets. In contrast, optimization-based approaches, which do not require labeled data, can adapt to individual instances but are sensitive to initialization. To address these challenges in solving real-world …
-
Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation
… for the real world. Training Unsupervised Domain Adaptation (UDA) models, using synthetic, automatically generated imagery, has shown promise in reducing reliance on manual labeling and improving the adaptation of features learned from the synthetic domain to the real-world domain of …
-
Generative 3D scene modeling: algorithm and applications
… scale is becoming increasingly important across domains such as agriculture, autonomous driving, immersive gaming, and robot learning. However, manually constructing such environments is prohibitively expensive and often introduces domain gaps from real-world distributions. Generative modeling of …
-
Open-world deep learning applied to pollen detection
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms