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 20 of 181 for “"Disentanglement"”.
-
Unwinding complexity: reflections on disentanglement
This thesis explores the material, emotional, and conceptual dimensions of weaving and unweaving as metaphors for navigating diasporic identity, cultural memory, and feminist resistance. Rooted in personal experience as an Iranian immigrant artist, the research positions textile …
-
Understanding Variational Autoencoders and Disentanglement Metrics
… between reconstruction fidelity and quality of disentanglement within the learnt representations. We validate the theory by conducting experiments on Frey's Faces image dataset using an encoder and decoder architecture using convolutional neural networks . In addition to this, we also learn what …
-
Computational solution and analysis of disentanglement puzzles
Disentanglement puzzles, as a type of mechanical puzzles whose goal is to separate pieces from each other. Traditionally these puzzles are designed for human entertainment, leaving reputations of challenging to solve. The intrinsic difficulty of such puzzles also poses various challenges to the …
-
ARCHITECTURAL DESIGN REPRESENTATION SPACES: DISENTANGLEMENT AND INTERPRETATION
… these spaces and addresses expressiveness, disentanglement, and diversity. The thesis also creates comprehensive design data repositories and conducts extensive experiments, providing pioneering insights and practical guidance for developing advanced design computing systems.
-
Disentanglement of Syntactic Components for Text Generation
Modelling human generated text, i.e., natural language data, is an important challenge in artificial intelligence. A good AI program should be able to understand and analyze natural language, and generate fluent and accurate responses. This standard is seen in applications of AI for natural …
-
A statistical evaluation of uncertainty disentanglement methods
Die Zerlegung prädiktiver Unsicherheit in eine aleatorische Komponente für die nicht reduzierbare Variabilität des datengenerierenden Prozesses und eine epistemische Komponente für den reduzierbaren Wissensmangel des Modells gilt im maschinellen Lernen inzwischen als Standard. Zugleich mehren sich …
-
Disentanglement Learning for Text-Free Voice Conversion
… as text-free systems. They commonly apply disentanglement learning methods to remove the speaker information of a speech signal, for example, vector quantisation (VQ) or instance normalisation (IN). However, text-free VC systems have not reached the same level of performance as …
-
Hierarchical part-based disentanglement of pose and appearance
Landmarks and keypoints are an important intermediate representation for image understanding and reconstruction. Although, many supervised approaches exist, these require labels of the target domain, which exist for humans, but only for sparse keypoints and not for the breadth of object and animal …
-
Pattern Discovery and Disentanglement for Clinical Data Analysis
… I have developed a novel Pattern Discovery and Disentanglement (PDD) Method to discover explicit patterns and unveil knowledge from relational datasets even encompassing imbalanced groups, biases and anomalies. The statistically significant high-order patterns, pattern clusters and rare patterns …
-
Deep Learning Models for Topic Classification and Disentanglement
… tasks in topic classification, clustering, and disentanglement. The capability of machines in understanding and modeling topics is a key component needed for developing many natural language understanding and generation applications. Despite the significant progress brought by deep learning, it …
-
Disentanglement in Representation Learning: Interpretability in Dimension Reduction With VAE
… correlation among ground truth factors influence disentanglement performance, using established metrics such as SAP and MIG, along with a newly proposed mutual information-based metric, $I_m$. Empirical evaluations on the dSprites dataset show that introducing explicit architectural constraints …
-
Capsule Networks: Framework and Application to Disentanglement for Generative Models
… networks. Thus, we attempt to increase the disentanglement of latent variables in variational autoencoders without compromising the generated image quality. In this thesis, a novel generative model based on capsule networks and a variational autoencoder is proposed. Motivated by the concept …
-
Parallel Disentanglement: Treaty-based Navigation of Settler-Indigenous Governance Politics
In this thesis, I outline a treaty-based interpretive and methodological framework for tending to settler-Indigenous governance relationships, while theorizing pathways towards more robust forms of settler solidarity and relational accountability to Indigenous legal geographies. I begin by …
-
Interpreting Deep Neural Networks and Beyond: Visualization, Learning Dynamics, and Disentanglement
… visualization, learning dynamics, and disentanglement. First, the demand for human interpretable explanations for model decisions has driven the development of visualization techniques. In particular, a class of backpropagation-based visualizations has attracted much attention recently, …
-
Deep Nuisance Disentanglement for Robust Object Detection from Unmanned Aerial Vehicles
… from the Abstract section of Deep Nuisance Disentanglement for Robust Object Detection from Unmanned Aerial Vehicles by Zhenyu Wu† , Karthik Suresh† , Priya Narayanan, Hongyu Xu, Heesung Kwon, Zhangyang Wang, 2019, International Conference on Computer Vision (ICCV 2019) Proceedings (Under …
-
DEEP LEARNING-BASED MOTION ESTIMATION AND DISENTANGLEMENT IN TAGGED MAGNETIC RESONANCE IMAGING
Quantifying internal tissue motion is essential for understanding organ function in cardiology, speech science, and neurotrauma research. Tagged magnetic resonance imaging (MRI) addresses this need by ``imprinting'' transient magnetization markers, i.e., tags, into tissue. Those tags deform with …
-
Controllable Gaze and Head-Pose Redirection via Latent Disentanglement in Convolutional Autoencoders
… in image space through autoencoder-based latent disentanglement. A custom data collection procedure is developed to enable dense and geometrically consistent supervision of gaze and head pose, supporting controlled learning of latent factors. Based on this data, convolutional autoencoders are …
-
SpeechSplit2: An efficient unsupervised speech disentanglement model for multi-aspect voice conversion
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-12-01
Page 1 of 10