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 12 of 12 for “"Domain discrepancy"”.
-
Sketch-based retrieval of images and 3D shapes.
… and 3D shape retrieval able to deal with a big domain discrepancy between 2D sketches and 3D shapes have not been well investigated. This thesis will address these issues. For the image retrieval, a single-colour sketch based image retrieval (SCSBIR) approach using RGB and HSV colour features is …
-
DEVELOPMENT OF DEEP LEARNING METHODS FOR PROGNOSTICS AND HEALTH MANAGEMENT
… network to transfer learning scenario. To reduce domain discrepancy caused by different working conditions, multi-layer adaptation based on multiple kernels is used. Owing to the availability of multiple labeled source domains, we then propose a unsupervised multi-source domain adaptation method …
-
Multi-Domain Adaptation for Image Classification, Depth Estimation, and Semantic Segmentation
… evaluated using images from the same scene and domain to avoid the domain gap. Recent advances in domain adaptation have led to a new type of method that bridges such domain gaps and learns from multiple domains. This dissertation proposes methods for multi-domain adaptation for various computer …
-
Training and Validation of Visual Perception Functions for Autonomous Driving with Synthetic Data
… data poses the problem of bridging the domain gap. This is true for both training and validating with synthetic images. Therefore, the domain gap has to be sufficiently understood to generate synthetically images viable to be used for training and validation. A new domain discrepancy …
-
Bridging distributional discrepancy with temporal dynamics for video understanding
… benefit video tasks, especially for the cross-domain case, which is close to real-world scenarios. Therefore, the objective of this thesis is to effectively exploit temporal dynamics from videos to tackle distributional discrepancy problems for video understanding. To achieve this objective, …
-
Data-Efficient Machine Learning with Focus on Transfer Learning
… data, 2) costly training process, and 3) domain discrepancy. Therefore, it is important to develop solutions for these problems, so the future of ML will be more sustainable. Recently, a new concept, data-efficient ma- chine learning (DEML), has been proposed to deal with the current …
-
Towards robust and reliable artificial intelligence in healthcare.
… expert-level performance across various domains, assisting with tasks of disease diagnosis/prognosis, drug discovery, and personalized treatment. As such applications have quickly proliferated in past decades, the effectiveness of AI tools, however, is contingent upon the quantity and …
-
Towards robust and reliable artificial intelligence in healthcare
… expert-level performance across various domains, assisting with tasks of disease diagnosis/prognosis, drug discovery, and personalized treatment. As such applications have quickly proliferated in past decades, the effectiveness of AI tools, however, is contingent upon the quantity and …
-
Graph and Subspace Learning for Domain Adaptation
… can not achieve good performance on the new domain. Domain adaptation algorithms are therefore designed to bridge the distribution gap between training (source) data and test (target) data. In this thesis, I propose two graph learning and two subspace learning methods for domain adaptation. …
-
Person Identification With Convolutional Neural Networks
… re-identification, we focus on the challenge of domain discrepancy between visible images and thermal images. We propose to address this issue at a class level with a CNN-based two-stream network. Specifically, our idea is to learn a center for features of each person in each domain (visible and …
-
Adversarial approaches to remote sensing image analysis
… want to address is the issue of semi-supervised domain adaptation. The goal of domain adaptation is to learn a generic classifier for multiple related problems, thereby reducing the cost of labeling. To that end, we propose two methods. The first method uses GANs in the context of image-to-image …
-
Vehicle re-identification from multi-modal vision sensors with deep metric learning
… used for model training, there is a considerable domain shift between training and testing data distributions. A typical issue arising in such setting is the over-fitting phenomenon that makes the model learn too well the training data and fail to generalise to the testing data. To mitigate this …