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 174 for “"self-supervised"”.

  1. Federated self-supervised learning

    … current FL practices predominantly focus on supervised learning tasks, necessitating the availability of high-quality, domain-specific labels alongside the data. This prerequisite constrains the implementation of FL in numerous real-world applications where access to such labels at the edge …

    cambridge Repository record for Federated self-supervised learning (opens in a new tab)

  2. Self-Supervised Learning for Geometry

    … deep learning problems. Differ from conventional supervised learning methods that using expensive annotations as the supervisory signal, we advocate for the use of geometry as a supervisory signal to improve the perceptual capabilities in robots, namely Geometry Self-supervision. With the geometry …

    adelaide Repository record for Self-Supervised Learning for Geometry (opens in a new tab)

  3. Structural Self-Supervised Objectives for Transformers

    In this Thesis, we leverage unsupervised raw data to develop more efficient pre-training objectives and self-supervised tasks that align well with downstream applications. In the first part, we present three alternative objectives to BERT’s Masked Language Modeling (MLM), namely Random Token …

    trento Repository record for Structural Self-Supervised Objectives for Transformers (opens in a new tab)

  4. Self-supervised multi-contrast MRI denoising

    … accuracy. This thesis presents the "Corruption2Self" (C2S) framework, a self-supervised method for multi-contrast MRI denoising. C2S utilizes self-generated pseudo-labels from noisy data to enhance contrast fusion and Signal-to-Noise Ratio (SNR), providing a robust solution that facilitates …

    uiuc Repository record for Self-supervised multi-contrast MRI denoising (opens in a new tab)

  5. Self-Supervised Learning for Speech Processing

    Deep neural networks trained with supervised learning algorithms on large amounts of labeled speech data have achieved remarkable performance on various spoken language processing applications, often being the state of the arts on the corresponding leaderboards. However, the fact that training …

    mit Repository record for Self-Supervised Learning for Speech Processing (opens in a new tab)

  6. Visual Domain Generalization via Self-Supervised Learning

    L'abstract è presente nell'allegato / the abstract is in the attachment

    poli-torino Repository record for Visual Domain Generalization via Self-Supervised Learning (opens in a new tab)

  7. Self-supervised learning frameworks for IoT applications

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-15 without embargo terms

    uiuc Repository record for Self-supervised learning frameworks for IoT applications (opens in a new tab)

  8. Structuring Representation Geometry in Self-Supervised Learning

    … We investigate this question in the context of self-supervised learning, a paradigm that extracts meaningful representations by leveraging the structure of the data itself without relying on explicit labels. Specifically, we propose adding additional geometric structure to the embedding space by …

    mit Repository record for Structuring Representation Geometry in Self-Supervised Learning (opens in a new tab)

  9. CellMincer: Self-Supervised Denoising of Functional Imaging

    … a model. This thesis introduces CellMincer, a self-supervised deep neural network for denoising functional imaging. By exploiting a combination of spatiotemporally local contexts and precomputed global features, CellMincer outperforms comparable algorithms at denoising several modes of optical …

    mit Repository record for CellMincer: Self-Supervised Denoising of Functional Imaging (opens in a new tab)

  10. Self-supervised Learning Methods for Vision-based Tasks

    … many machine learning models. Among them, self-supervised learning appears as an efficient solution capable of training powerful and generalizable models. More specifically, instead of relying on human-generated labels, it proposes training objectives that use ``labels'' generated from the …

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

  11. Self-supervised Learning of Monocular Depth from Video

    … problem of monocular depth estimation via self-supervised learning from RGB-only videos. Although existing work has shown partial excellent results in benchmark datasets, there remain several vital challenges that limit the use of these algorithms in general scenarios. To summarize, my …

    adelaide Repository record for Self-supervised Learning of Monocular Depth from Video (opens in a new tab)

  12. Self-Supervised Audio-Visual Speech Diarization and Recognition

    Many real world use cases of automatic speech recognition (ASR) contain video and multiple speakers, such as TV broadcasts and video conferences. However, state-of-the-art end-to-end multimodal ASR models generally do not support diarization. This thesis extends one such model, AV-HuBERT, to …

    mit Repository record for Self-Supervised Audio-Visual Speech Diarization and Recognition (opens in a new tab)

  13. SLAM-aware, self-supervised perception in mobile robots

    … ability to perform GP Saided SLAM, we develop a self-supervised visual-Slam front-end capable of performing visual ego-motion, and vision-based loop-closure recognition in mobile robots. We propose a novel, generative model solution that it is able to predict ego-motion estimates from optical …

    mit Repository record for SLAM-aware, self-supervised perception in mobile robots (opens in a new tab)

  14. Self-Supervised ECG Learning for Multimodal Clinical Tasks

    … combinations. We first introduce ECG-JEPA, a self-supervised encoder pretrained on multiple ECG datasets to learn generalizable time series representations. This unimodal pretraining improves ECG classification, achieving a 23-point AUC gain on the underrepresented Ga dataset. We then align …

    mit Repository record for Self-Supervised ECG Learning for Multimodal Clinical Tasks (opens in a new tab)

  15. Self-supervised Learning for IMU-based Human Activity Recognition

    … units. In this thesis, we propose the use of self-supervised learning for human activity recognition using the tri-axial data collected from the smartphone-embedded accelerometers. To address the limitations of fully-supervised learning, mainly reliance on labeled data, we propose two …

    queens Repository record for Self-supervised Learning for IMU-based Human Activity Recognition (opens in a new tab)

  16. Contrasting with adversarial examples improves self-supervised representation learning

    DSpace SAF Submission Ingestion Package generated from Vireo submission #18414 on 2022-11-16 at 10:56:42

    uiuc Repository record for Contrasting with adversarial examples improves self-supervised representation learning (opens in a new tab)

  17. Self-supervised learning of spatiotemporal features from video colorization

    The student, Zubin Pahuja, accepted the attached license on 2019-07-19 at 13:10.

    uiuc Repository record for Self-supervised learning of spatiotemporal features from video colorization (opens in a new tab)

  18. Self-supervised learning for data-efficient human activity recognition

    … data-efficient. First, we proposed a new semi-supervised training pipeline that combines self-supervised learning and knowledge distillation to effectively leverage large-scale unlabelled datasets for human activity recognition. This helps models generalise better across different users by …

    cambridge Repository record for Self-supervised learning for data-efficient human activity recognition (opens in a new tab)

Page 1 of 9