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 17 of 17 for “"unsupervised domain adaptation"”.
-
Unsupervised Domain Adaptation per la rilevazione di oggetti e riconoscimento di azioni
Questa tesi affronta il problema di unsupervised domain adaptation (UDA) per la rilevazione degli oggetti e il riconoscimento delle azioni. UDA è una tecnica di machine learning che mira a ridurre le differenze di distribuzione tra un dominio di origine (con dati etichettati) e un dominio di …
-
Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation
We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling …
-
Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation
… annotated datasets for the real world. Training Unsupervised Domain Adaptation (UDA) models, using synthetic, automatically generated imagery, has shown promise in reducing reliance on manual labeling and improving the adaptation of features learned from the synthetic domain to the real-world …
-
Multi-source domain adaptation with mixture of experts
We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine …
-
Transfer Learning For Spoken Language Processing
… applications. In particular, we tackle domain adaptation in the context of Automatic Speech Recognition (ASR) and Cross-Lingual Learning in Automatic Speech Translation (AST). The first part of the thesis develops an algorithm for unsupervised domain adaptation of End-to-End ASR models. …
-
Learning without Labels - Reducing Supervision in Training, Inference, and Evaluation of Deep Neural Networks
… pipeline. In the training phase, we explore unsupervised fine-tuning, focusing on Source-Free Unsupervised Domain Adaptation scenarios in visual tasks such as Facial Expression Recognition and video-based Action Recognition, primarily leveraging self-supervision and self-training. At …
-
Self-supervised Learning Methods for Vision-based Tasks
… scalable, and easy to use; two papers tackling unsupervised domain adaptation in action recognition; and one paper on self-supervised learning for continual learning. The published papers highlight that self-supervised techniques can be leveraged for many scenarios, yielding state-of-the-art …
-
Towards Generalization of Models on Streets Imagery: Methods and Applications
The domains relevant to urban planning have been disrupted by the proliferation of highly granular city data and the advancements in machine learning. However, machine learning models are susceptible to pitfalls constraining their deployment in many applications including domains related to urban …
-
Towards Comprehensive Visual Understanding via Deep Neural Networks
… extensive annotation for different scenes (domains) and separates the understanding of semantic targets into distinct tasks, designing meticulous networks and corresponding optimization for each. This poses challenges from two perspectives: i) generalizing from one domain to another, and ii) …
-
Unsupervised learning of disentangled representations for speech with neural variational inference models
… that an essential component of human learning is unsupervised or weakly supervised representation learning, which transforms input signals to low dimensional representations that facilitate subsequent structured learning and knowledge acquisition. In this thesis, we develop unsupervised …
-
Overcoming resource limitations in the processing of unlimited speech : applications to speaker and language recognition
… data. In particular, successful methods in unsupervised domain adaptation can automatically recognize and adapt existing algorithms to systematic changes in the input. Furthermore, methods that can organize incoming streams of information can allow us to derive insights with minimal manual …
-
Knowledge transfer in vision tasks with incomplete data
… of existing classifiers. Second, with unsupervised domain adaptation where the target domain annotations are unavailable, we propose a method to more effectively transfer models to the unsupervised target domain, but guiding it using a common auxiliary task whose ground truth can be …
-
Guiding Deep Probabilistic Models
… demonstrate the effectiveness of our approach in unsupervised domain adaptation under label distribution shift. Recent works have shown that under cross-domain label distribution shift, optimizing for distribution alignment is excessively restrictive and causes performance degradation. Our …
-
Action Recognition with Knowledge Transfer
… I formulate human action recognition as an unsupervised domain adaptation (UDA) problem to handle the second problem. In the UDA setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already exist- ing labeled video datasets as source data in …
-
Beyond rules: leveraging Large Language Models for code-data separation in binary disassembly
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01
-
Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels
… of distribution discrepancies between these domains, directly training the model on the source domain cannot be expected to generate satisfactory results on the target domain. Therefore, the problem of minimizing these data distribution discrepancies is the main challenge with which modern …
-
Deep learning for grouped data
… potential to unlock solutions in many important domains of machine learning, including disentangling the generative factors of data, performing missing data imputation, or training robust predictors. However, grouped data also comes with challenges, especially when the data is high-dimensional …