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 10 of 10 for “"Sparsely annotated"”.
-
Sparsely Annotated Semantic Segmen tation of Weather-Related Road Surface Conditions
… segmentation, which relies heavily on densely annotated datasets that require significant manual labor to generate, this project utilises sparsely annotated data. These sparse labels, though containing less information, substantially reduce the need for manual annotation. Additionally, the …
-
Analysis of mixture of experts on individual, sparsely-annotated and multi-dataset object detection
… this mixing problem by creating synthetic sparsely-annotated splits of COCO and VOC datasets which have annotations of a set of classes removed. These splits also evaluate the missing annotation noise that is often found in large-scale annotated datasets. Ensemble learning can be an optimal …
-
Semi-supervised learning algorithm to estimate mass flow from sparsely annotated images using a vision system (SLEM)
… and sugarcane) is accurately predicted from sparsely annotated images by training a deep neural network (DNN) in a semi-supervised fashion using only final load weights. The DNN succeeds in capturing the complex density physics of random stacking of slender rods as part of the mass prediction …
-
3D Hand Shape and Pose Estimation
… shape and pose in a video dataset given only sparsely annotated frames. We propose label propagation to propagate 3D annotations from labelled frames to nearby unlabelled frames. Next, we address the problem of probabilistic 3D hand shape and pose estimation. Most existing works only estimate …
-
TOWARDS EFFICIENT VIDEO PERCEPTION AND GENERATION
… video, enabling robust online learning from sparsely annotated data and achieving state-of-the-art performance with only 25% of the labels. Second, we introduce Tune-A-Video, a one-shot fine-tuning approach that adapts pre-trained text-to-image diffusion models for video generation using a …
-
Deep learning for protein function prediction
… predicting functions for proteins that are sparsely annotated, particularly in few-shot or zero-shot settings. In addition to proposing novel models, this work discusses practical challenges in multimodal learning for biology, strategies for combining heterogeneous data sources, and …
-
Algorithms to Explore the Structure and Evolution of Biological Networks
… the structure and evolution of large, noisy, and sparsely annotated biological networks. We first introduce two information-theoretic algorithms to extract interesting patterns and modules embedded in large graphs. The first, graph summarization, uses the minimum description length principle to …
-
Integration of physical prior knowledge in machine learning imaging workflows
… on the downstream model due to missing data in sparsely annotated datasets. In this thesis, we developed a generative framework based on diffusion models for the synthesis of lung cancer tissue histological data. The model leverages the biological insight on the macroscopic cell arrangement to …
-
If Not for Her Sex: The Mysterious Education of American Women, 1750-1850
… and lower class women, in 1750-1850, has been sparsely annotated in historical research. Historical research hinted that these women were educated far beyond the “female arts,” but little else was written to indicate how women, without substantial means, were able to acquire higher education. …
-
Benchmarks, Data, and Evaluation for Robust Retrieval and Retrieval-Augmented Generation on Heterogeneous Domains and Languages
… fine-tune retrievers is often noisy, imbalanced, sparsely annotated, and scarcely available in non-English languages, so that increasing scale through mixtures of supervised and synthetic data does not reliably translate into improved robustness without principled curation. Third, evaluating RAG …