Matches in SemOpenAlex for { <https://semopenalex.org/work/W3191997717> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3191997717 abstract "In recent years, machine learning methods especially supervised learning methods have achieved great progress in both methodologies and applications. However, in supervised learning, each training sample requires a label to indicate its ground-truth. In many machine learning tasks, it is hard to get sufficient accurately labelled training samples. Weakly supervised learning is an extended setting of supervised learning to more general tasks. In this thesis, we focus on proposing novel methods for inaccurate supervision and incomplete supervision under the setting of weakly supervised learning. In inaccurate supervision, problems with nondeterministic labels, such as stochastic supervision problems, are rarely discussed. In stochastic supervision, the supervision is a probabilistic assessment rather than a deterministic label. In Chapter 2, we provide four generalisations of stochastic supervision models, extending them to asymmetric assessments, multiple classes, feature-dependent assessments, and multi-modal classes, respectively. Corresponding to these generalisations, four new EM algorithms are derived. We show the effectiveness of our generalisations through illustrative examples of simulated datasets, as well as real-world examples of two famous datasets, the MNIST dataset, and the CIFAR-10 dataset. For incomplete supervision problems, we focus on improving the semi-supervised learning in one domain/task by transferring knowledge from another domain/task or from many domains/tasks. In Chapter 3, a novel domain-adaptation-based method is proposed to improve a typical application of semi-supervised learning: the pose estimation, in which the implicit density estimation problem in the domain adaptation is solved by using a neural network to approximate it. The proposed method transfers the knowledge from the training samples in the synthetic data domain to improve the learner in the real data domain, and achieves state-of-the-art performance. In Chapter 4, we focus on transferring knowledge from many tasks to improve the semi-supervised few-shot learning. We use meta-learning to transfer knowledge from many meta-train tasks. A tailor-made ensemble method for few-shot learning is proposed to relieve the pseudo-label noise problem in the semi-supervised few-shot learning. The proposed method also achieves state-of-the-art performances in two widely used benchmark datasets (miniImageNet and tieredImageNet) in few-shot learning." @default.
- W3191997717 created "2021-08-16" @default.
- W3191997717 creator A5042218507 @default.
- W3191997717 date "2021-02-28" @default.
- W3191997717 modified "2023-09-26" @default.
- W3191997717 title "Weakly supervised learning with stochastic supervision and knowledge transfer" @default.
- W3191997717 hasPublicationYear "2021" @default.
- W3191997717 type Work @default.
- W3191997717 sameAs 3191997717 @default.
- W3191997717 citedByCount "0" @default.
- W3191997717 crossrefType "dissertation" @default.
- W3191997717 hasAuthorship W3191997717A5042218507 @default.
- W3191997717 hasConcept C119857082 @default.
- W3191997717 hasConcept C120665830 @default.
- W3191997717 hasConcept C121332964 @default.
- W3191997717 hasConcept C134306372 @default.
- W3191997717 hasConcept C136389625 @default.
- W3191997717 hasConcept C138885662 @default.
- W3191997717 hasConcept C150899416 @default.
- W3191997717 hasConcept C154945302 @default.
- W3191997717 hasConcept C162324750 @default.
- W3191997717 hasConcept C187736073 @default.
- W3191997717 hasConcept C190502265 @default.
- W3191997717 hasConcept C192209626 @default.
- W3191997717 hasConcept C2776401178 @default.
- W3191997717 hasConcept C2780451532 @default.
- W3191997717 hasConcept C33923547 @default.
- W3191997717 hasConcept C36503486 @default.
- W3191997717 hasConcept C41008148 @default.
- W3191997717 hasConcept C41895202 @default.
- W3191997717 hasConcept C49937458 @default.
- W3191997717 hasConcept C50644808 @default.
- W3191997717 hasConcept C58973888 @default.
- W3191997717 hasConceptScore W3191997717C119857082 @default.
- W3191997717 hasConceptScore W3191997717C120665830 @default.
- W3191997717 hasConceptScore W3191997717C121332964 @default.
- W3191997717 hasConceptScore W3191997717C134306372 @default.
- W3191997717 hasConceptScore W3191997717C136389625 @default.
- W3191997717 hasConceptScore W3191997717C138885662 @default.
- W3191997717 hasConceptScore W3191997717C150899416 @default.
- W3191997717 hasConceptScore W3191997717C154945302 @default.
- W3191997717 hasConceptScore W3191997717C162324750 @default.
- W3191997717 hasConceptScore W3191997717C187736073 @default.
- W3191997717 hasConceptScore W3191997717C190502265 @default.
- W3191997717 hasConceptScore W3191997717C192209626 @default.
- W3191997717 hasConceptScore W3191997717C2776401178 @default.
- W3191997717 hasConceptScore W3191997717C2780451532 @default.
- W3191997717 hasConceptScore W3191997717C33923547 @default.
- W3191997717 hasConceptScore W3191997717C36503486 @default.
- W3191997717 hasConceptScore W3191997717C41008148 @default.
- W3191997717 hasConceptScore W3191997717C41895202 @default.
- W3191997717 hasConceptScore W3191997717C49937458 @default.
- W3191997717 hasConceptScore W3191997717C50644808 @default.
- W3191997717 hasConceptScore W3191997717C58973888 @default.
- W3191997717 hasLocation W31919977171 @default.
- W3191997717 hasOpenAccess W3191997717 @default.
- W3191997717 hasPrimaryLocation W31919977171 @default.
- W3191997717 hasRelatedWork W1495442604 @default.
- W3191997717 hasRelatedWork W2117729721 @default.
- W3191997717 hasRelatedWork W2117977096 @default.
- W3191997717 hasRelatedWork W2160326647 @default.
- W3191997717 hasRelatedWork W2397800115 @default.
- W3191997717 hasRelatedWork W2429093498 @default.
- W3191997717 hasRelatedWork W2742267824 @default.
- W3191997717 hasRelatedWork W2809669277 @default.
- W3191997717 hasRelatedWork W2854328664 @default.
- W3191997717 hasRelatedWork W2942724771 @default.
- W3191997717 hasRelatedWork W2965142139 @default.
- W3191997717 hasRelatedWork W2995113766 @default.
- W3191997717 hasRelatedWork W3161622534 @default.
- W3191997717 hasRelatedWork W3176055902 @default.
- W3191997717 hasRelatedWork W3176894913 @default.
- W3191997717 hasRelatedWork W3177393777 @default.
- W3191997717 hasRelatedWork W3183472812 @default.
- W3191997717 hasRelatedWork W3183977392 @default.
- W3191997717 hasRelatedWork W3190288121 @default.
- W3191997717 hasRelatedWork W75318427 @default.
- W3191997717 isParatext "false" @default.
- W3191997717 isRetracted "false" @default.
- W3191997717 magId "3191997717" @default.
- W3191997717 workType "dissertation" @default.