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 5 of 5 for “"Foundation Model Adaptation"”.
-
Label-Efficient 3D Point Cloud Understanding: From Representation Learning to Foundation Model Adaptation
… on raw point clouds to adapting pre-trained 3D foundation models under limited supervision and distribution shift. We first address representation learning by proposing CrossMoCo, a cross-modal momentum-contrastive framework that jointly pre-trains point cloud and image encoders to learn …
-
Multimodal Representation Learning for Face Understanding: From Caption Supervision to Foundation Model Adaptation
… occlusion. While Vision Transformer (ViT)-based foundation models have greatly improved visual representation learning, their patch-based tokenization and lack of spatial inductive bias limit their ability to capture fine-grained details in low-resolution inputs. This dissertation investigates …
-
Multicultural representation learning for music signal analysis
… systematic evaluation of deep audio embedding models across Western, Mediterranean, and Indian musical traditions. To address limited annotated data challenges, the dissertation introduces Label-Combination Prototypical Networks (LC-Protonets), a novel multi-label few-shot learning approach …
-
Machine Learning Toward Materials Discovery: From Crystal Mapping and Out-of-Distribution Property Prediction to Radiation Detection and Emerging Foundation Models.
… learning for out-of- distribution prediction, foundation-model-based property prediction, and deep neural classifcation of photon interactions. A global mapping framework is frst introduced to analyze the inorganic materials space using compositional, structural, physical, and neural …
-
Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning
… for joint training. Instead, locally trained models are exchanged with a central server, which aggregates the knowledge from all of the uploaded models and then distributes a refined global model to each party. This approach allows each party to benefit from the collective contributions, …