Sökning: "IoU Prediction"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden IoU Prediction.

  1. 1. Explainability Methods for Transformer-based Artificial Neural Networks: : a Comparative Analysis

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

    Författare :Eliott Remmer; [2022]
    Nyckelord :XAI; NLP; Transformers; BERT; explainable predictions; SHAP; Attention; XAI; NLP; Transformers; BERT; förklarbara förutsägelser; SHAP; Attention;

    Sammanfattning : The increasing complexity of Artificial Intelligence (AI) models is accompanied by an increase in difficulty in interpreting model predictions. This thesis work provides insights and understanding of the differences and similarities between explainability methods for AI models. LÄS MER

  3. 2. Road Segmentation and Optimal Route Prediction using Deep Neural Networks and Graphs

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Viktor Ossmark; [2021]
    Nyckelord :statistics; applied mathematics; machine learning; computer vision; deep learning; satellite data; remote sensing; image segmentation; optimal routing; deep neural networks; graphs; AI; statistik; tillämpad matematik; maskininlärning; djup inlärning; datorseende; satellitdata; bildsegmentering; optimala rutter; grafer; AI;

    Sammanfattning : Observing the earth from above is a great way of understanding our world better. From space, many complex patterns and relationships on the ground can be identified through high-quality satellite data. LÄS MER

  4. 3. Improving Situational Awareness in Aviation: Robust Vision-Based Detection of Hazardous Objects

    Master-uppsats, Mälardalens högskola/Akademin för innovation, design och teknik

    Författare :Alexandra Levin; Najda Vidimlic; [2020]
    Nyckelord :Object Detection; Custom Data Set; Faster RCNN; ResNet-50-FPN; Aviation; Situational Awareness;

    Sammanfattning : Enhanced vision and object detection could be useful in the aviation domain in situations of bad weather or cluttered environments. In particular, enhanced vision and object detection could improve situational awareness and aid the pilot in environment interpretation and detection of hazardous objects. LÄS MER

  5. 4. Polyp segmentation using artificial neural networks

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

    Författare :Antoni Rodríguez Villegas; [2020]
    Nyckelord :Semantic segmentation; Polyp segmentation; Neural Networks; Computer Vision; ANN; FCN; Deep Learning; Colorectal cancer;

    Sammanfattning : Colorectal cancer is the second cause of cancer death in the world. Aiming to early detect and prevent this type of cancer, clinicians perform screenings through the colon searching for polyps (colorectal cancer precursor lesions).If found, these lesions are susceptible of being removed in order to further ana-lyze their malignancy degree. LÄS MER

  7. 5. Breast Cancer Risk Localization in Mammography Images using Deep Learning

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

    Författare :Beata Rystedt; [2020]
    Nyckelord :Deep learning; breast cancer risk; mammograms; convolutional networks; localization.; Djupinlärning; bröstcancerrisk; mammogram; faltningsnätverk; lokalisering.;

    Sammanfattning : Breast cancer is the most common form of cancer among women, with around 9000 new diagnoses in Sweden yearly. Detecting and localizing risk of breast cancer could give the opportunity for individualized examination programs and preventative measures if necessary, and potentially be lifesaving. LÄS MER