Essays about: "Consistency Regularization"

Found 3 essays containing the words Consistency Regularization.

  1. 1. Semi-Supervised Domain Adaptation for Semantic Segmentation with Consistency Regularization : A learning framework under scarce dense labels

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Daniel Morales Brotons; [2023]
    Keywords : Domain Adaptation; Semi-Supervised Learning; Semi-Supervised Domain Adaptation; Semantic Segmentation; Consistency Regularization; Domain Adaptation; Semi-Supervised Learning; Semi-Supervised Domain Adaptation; Semantisk Segmentering; Konsistensregularisering;

    Abstract : Learning from unlabeled data is a topic of critical significance in machine learning, as the large datasets required to train ever-growing models are costly and impractical to annotate. Semi-Supervised Learning (SSL) methods aim to learn from a few labels and a large unlabeled dataset. READ MORE

  2. 2. An Industrial Application of Semi-supervised techniques for automatic surface inspection of stainless steel. : Are pseudo-labeling and consistency regularization effective in a real industrial context?

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Mattia Zoffoli; [2022]
    Keywords : Deep Learning; Computer Vision; Semi-Supervised Learning; Automatic Inspection; Stainless Steel; Djupt lärande; datorseende; Semi-övervakat lärande; Automatisk inspektion; Rostfritt stål;

    Abstract : Recent developments in the field of Semi-Supervised Learning are working to avoid the bottleneck of data labeling. This can be achieved by leveraging unlabeled data to limit the amount of labeled data needed for training deep learning models. READ MORE

  3. 3. Semi-Supervised Methods for Classification of Hyperspectral Images with Deep Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Oscar Örnberg; [2020]
    Keywords : ;

    Abstract : Hyperspectral images (HSI) can reveal more patterns than regular images. The dimensionality is high with a wider spectrum for each pixel. Few labeled datasets exists while unlabeled data is abundant. This makes semi-supervised learning well suited for HSI classification. READ MORE