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 18 of 18 for “"Disentangled representation learning"”.
-
Anomaly Detection Based on Disentangled Representation Learning
… discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner. The t-Distributed Stochastic Neighbor Embedding (t-SNE), an unsupervised non-linear technique primarily used for data exploration and visualizing high-dimensional data, has …
-
Disentangled Representation Learning for Stylistic Variation in Neural Language Models
… network has proven to be an effective machine learning method over the past decade, prompting its usage for modelling language, among several other domains. However, the latent representations learned by these neural network function approximators remain uninterpretable, resulting in a new wave …
-
ARCHITECTURAL DESIGN REPRESENTATION SPACES: DISENTANGLEMENT AND INTERPRETATION
… computational techniques for design feature representation and interpretation. Few existing theoretical models provide the necessary prescriptive and predictive insights, while understanding the implication of latent design spaces is crucial. This thesis re-examines the theoretical foundation …
-
Disentanglement in Representation Learning: Interpretability in Dimension Reduction With VAE
… both theoretical and practical aspects of disentangled representation learning by extending the VAE framework. We address the core challenge of extracting independent generative factors from observed data while preserving high reconstruction fidelity. To this end, we propose two novel VAE …
-
Yet another image clustering framework using deep learning
Unsupervised disentangled representation learning is a long-standing problem in computer vision. This thesis aims to tackle this problem and proposes a deep learning framework for performing image clustering. More specifically, this work proposes a novel framework for performing image clustering …
-
Exploring Knowledge Transfer with Deep Learning
<p>Deep learning methods have achieved significant success when trained on large amounts of data. However, in many real-world applications, data are either too expensive or impossible to collect. Therefore, how to take advantage of the knowledge acquired from one context with adequate amounts of …
-
Visual Representation Learning with Progressive Data Scarcity.
One of the key advantages of supervised deep learning over conventional machine learning is that the learning process of a neural network does not rely directly on hand-crafted features. There is no denying that the availability of large-scale annotated data plays a vital role in the success of …
-
Combinatorial Generalisation in Machine Vision
… systems and others the benefits of distributed representations. In this thesis we will explore which principles help AI systems to generalise to novel combinations of previously observed elements (such as color and shape) in the context of machine vision. We will show that while approaches such …
-
Video Action Understanding: Action Classification, Temporal Localization, And Detection
… view and action queries, to enforce the learning of action features robust to shifts in viewpoints. Next, we focus on temporal action localization (``What?" and ``When?") and address challenges introduced in the multi-label setting. Our proposed solution involves leveraging the inherent …
-
Training deep generative models via lifelong learning
Lifelong learning represents an essential function of an artificial intelligence system, which can continually acquire and learn novel knowledge without forgetting it. Lately, deep learning has brought new possibilities for the development of artificial intelligence, including artificial lifelong …
-
Numerical Methods in Deep Learning and Computer Vision
… used in the field of computer vision and deep learning. In this thesis, we investigate the algorithms of some numerical methods and their relevant applications in deep learning. These studied numerical techniques mainly include differentiable matrix power functions, differentiable …
-
Semi-supervised learning for annotation and representation of single-cell rna sequencing and spatial transcriptomics data
<p>Semi-supervised learning has emerged as a powerful paradigm for analyzing single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data, where full annotation is often costly or impractical. scRNA-seq technologies measure the expression of thousands of genes across tens of …
-
Unbiased Representation Learning Networks for Single Rainy Image Restoration
… However, by evaluating representative deep-learning based deraining models on benchmark datasets, two unfavorable results are obtained: (1) they cannot handle various rainy conditions (i.e., rains of various directions and densities) equally well, and (2) the models trained on synthetic …
-
METHODS FOR AUTOMATED ANALYSIS OF RETINAL OCT AND OCTA IMAGES
… In light of the advancements in deep learning and the constraints posed by limited manual labels for OCTA images, we propose two deep learning-based algorithms for efficient segmentation with reduced dependency on manual labels. We first introduce variational intensity cross channel …
-
Expanding the Frontier of Speaker-Adaptive TTS: Stronger Generalisation, Less Storage, Wider Languages
… zero-shot speaker-adaptive model that introduces disentangled representation learning together with adversarial discriminators to strengthen the model’s voice generalisation. On the data side, this thesis introduces a new TTS corpus with diverse accents to further improve voice robustness during …
-
Automatic assessment and enhancement of streaming video quality under bandwidth and dynamic range limitations
… state-of-the-art accuracy. Finally, the deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks share a common theme …
-
Deep Learning for Breast Image Analysis: Current Progress and Future Work
<p>Deep learning has revolutionized medical image analysis, yet its application to breast imaging faces unique challenges stemming from high anatomical variability, subtle disease features, limited labeled data, and domain shift across imaging acquisition parameters. This dissertation addresses …
-
Autoencoder-based deep learning methods for single cell and spatial transcriptomics
… In this thesis, we develop and explore deep learning-based methods to address these challenges through the lens of autoencoder architectures. In Chapter 1, we benchmark Variational Autoencoders (VAEs) against traditional linear decomposition methods, demonstrating that VAEs more effectively …