Sökning: "state of the art SSL"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden state of the art SSL.

  1. 1. Semi-Supervised Head Detection for Low Resolution Images

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Annie Biby Rapheal; [2023]
    Nyckelord :Object detection; Semi Supervised Learning; Head detection; Objektdetektion; Semisupervised Learning; Huvuddetektion;

    Sammanfattning : Object detection is a widely researched and applied field in computer vision. Deep learning models have successfully been used for object detection over the years. The performance of State of the art (SOTA) object detection deep learning models is dependent on the number of labeled images. LÄS MER

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

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Daniel Morales Brotons; [2023]
    Nyckelord :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;

    Sammanfattning : 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. LÄS MER

  4. 3. Sound Source Localization for an Urban Outdoor Setting : A Systematic Review

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Anna Malmgren; [2022]
    Nyckelord :sound source localization; outdoor localization; state of the art SSL;

    Sammanfattning : Sound source localization (SSL) is a broad field, with many important application areas. In outdoor environments SSL systems can, among other things, be used to increase citizens’ safety by detecting and locating abnormal sounds such as gunshots or screams. LÄS MER

  5. 4. Semi- Supervised and Fully Supervised Learning for Fashion Images : A Comparison Study

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Carl Mannerstråle; [2021]
    Nyckelord :Semi- Supervised Learning; Convolutional Neural Networks; Fashion E- Commerce; Fashion Classification; Deep Learning; Labeled Data; Semi- Övervakad Inlärning; Djupa Neurala Nätverk; Mode E- handel; Klassificering av Modebilder; Djupinlärning; Annoterad Data;

    Sammanfattning : Image recognition is a subfield in computer vision, representing a set of methods for analyzing images. Image recognition systems allow computers to automatically find patterns and draw conclusions directly from images. LÄS MER

  7. 5. Effectiveness of fuzz testing high-security applications

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Balthazar West; Marcus Wengelin; [2017]
    Nyckelord :;

    Sammanfattning : Fuzzing is a testing methodology that is receiving increased attention in the field of software security. The methodology is interesting because almost anyone can download a fuzzer and search for bugs in large and well-tested programs or libraries. LÄS MER