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"”.

  1. 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 …

    catania Repository record for Unsupervised Domain Adaptation per la rilevazione di oggetti e riconoscimento di azioni (opens in a new tab)

  2. 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 …

    uiuc Repository record for Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation (opens in a new tab)

  3. 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 …

    houston Repository record for Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation (opens in a new tab)

  4. 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 …

    mit Repository record for Multi-source domain adaptation with mixture of experts (opens in a new tab)

  5. 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. …

    mit Repository record for Transfer Learning For Spoken Language Processing (opens in a new tab)

  6. 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 …

    trento Repository record for Learning without Labels - Reducing Supervision in Training, Inference, and Evaluation of Deep Neural Networks (opens in a new tab)

  7. 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 …

    trento Repository record for Self-supervised Learning Methods for Vision-based Tasks (opens in a new tab)

  8. 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 …

    mit Repository record for Towards Generalization of Models on Streets Imagery: Methods and Applications (opens in a new tab)

  9. 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) …

    uts Repository record for Towards Comprehensive Visual Understanding via Deep Neural Networks (opens in a new tab)

  10. 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

    mit Repository record for Unsupervised learning of disentangled representations for speech with neural variational inference models (opens in a new tab)

  11. 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 …

    mit Repository record for Overcoming resource limitations in the processing of unlimited speech : applications to speaker and language recognition (opens in a new tab)

  12. 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 …

    uiuc Repository record for Knowledge transfer in vision tasks with incomplete data (opens in a new tab)

  13. 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 …

    mit Repository record for Guiding Deep Probabilistic Models (opens in a new tab)

  14. 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 …

    vt Repository record for Action Recognition with Knowledge Transfer (opens in a new tab)

  15. 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

    uiuc Repository record for Beyond rules: leveraging Large Language Models for code-data separation in binary disassembly (opens in a new tab)

  16. 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 …

    vt Repository record for Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels (opens in a new tab)

  17. 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 …

    cambridge Repository record for Deep learning for grouped data (opens in a new tab)