Essays about: "data augmentations"

Showing result 16 - 20 of 37 essays containing the words data augmentations.

  1. 16. Evaluating the effects of data augmentations for specific latent features : Using self-supervised learning

    University essay from KTH/Hälsoinformatik och logistik

    Author : Markus Ingemarsson; Jacob Henningsson; [2022]
    Keywords : Contrastive learning; data augmentations; deep learning; invariant features; machine learning; representation similarity analysis; self-supervised learning; SimCLR; Kontrast inlärning; datamodifieringar; djupinlärning; maskininlärning; SimCLR; självövervakat lärande; oföränderliga egenskaper; representativ likhetsanalys;

    Abstract : Supervised learning requires labeled data which is cumbersome to produce, making it costly and time-consuming. SimCLR is a self-supervising framework that uses data augmentations to learn without labels. This thesis investigates how well cropping and color distorting augmentations work for two datasets, MPI3D and Causal3DIdent. READ MORE

  3. 17. The research of background removal applied to fashion data : The necessity analysis of background removal for fashion data

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

    Author : Junhui Liang; [2022]
    Keywords : Background Removal; Fashion Analysis; Salient Object Detection;

    Abstract : Fashion understanding is a hot topic in computer vision, with many applications having a great business value in the market. It remains a difficult challenge for computer vision due to the immense diversity of garments and a wide range of scenes and backgrounds. READ MORE

  4. 18. Augmentation for Generalization

    University essay from Lunds universitet/Matematik LTH

    Author : Joel Ottosson; [2022]
    Keywords : machine learning; microscopy; segmentation; augmentation; neural network; Mathematics and Statistics;

    Abstract : To be able to automatically segment cells in microscopic images would give biologist a new tool to gather crucial data in quantities not possible by manual work. This is however not a trivial problem and has proven to be very difficult, especially if the images are in 3D. READ MORE

  5. 19. Exploring Text Augmentations For Swedish

    University essay from Stockholms universitet/Institutionen för data- och systemvetenskap

    Author : Mosleh Mahamud; [2022]
    Keywords : ;

    Abstract : Text Augmentation has been given very little attention in the Swedish text domains. Hence, applying popular techniques like EDA, Type-specific synonym replacement and Text Fragmentation has not been explored on datasets such as linguistic acceptability and aspect-based sentiment analysis. READ MORE

  6. 20. Noisy recognition of perceptual mid-level features in music

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

    Author : Simon Mossmyr; [2021]
    Keywords : ;

    Abstract : Self-training with noisy student is a consistency-based semi-supervised self- training method that achieved state-of-the-art accuracy on ImageNet image classification upon its release. It makes use of data noise and model noise when fitting a model to both labelled data and a large amount of artificially labelled data. READ MORE