Essays about: "Cityscapes"

Showing result 11 - 15 of 25 essays containing the word Cityscapes.

  1. 11. One-Shot Neural Architecture Search for Deep Multi-Task Learning in Computer Vision

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

    Author : Gianluigi Silvestri; [2020]
    Keywords : ;

    Abstract : In this work, a neural architecture search algorithm for multi-task learning is proposed. Given any dataset and tasks group, the method aims to find the optimal way of sharing layers among tasks in convolutional neural networks. READ MORE

  3. 12. Vertal HEX : Mobility for the future vertical cityscape

    University essay from Umeå universitet/Designhögskolan vid Umeå universitet

    Author : Simon Turac; [2020]
    Keywords : vertical mobility; future mobility; magnetic levitation; interior design; exterior design; vehicle design;

    Abstract : The project originated with the question "What is the future of urban mobility?" and the counterquestion "What is the future of urbanity?". To understand the future of mobility, we first need to try to understand more of the future context where it'll reside. READ MORE

  4. 13. När skyarna faller : publika platser med hållbar skyfallshantering i den förtätade staden

    University essay from SLU/Dept. of Landscape Architecture, Planning and Management (from 130101)

    Author : Millicent Skogsmyr; [2019]
    Keywords : hållbar skyfallsplanering; öppen dagvattenhantering; klimatförändringar; grönblå infrastruktur; förtätning;

    Abstract : På grund av världens pågående globala uppvärmning som sker till följd av förbränning av fossila bränslen kommer vädret och klimatet att förändras inom det närmaste århundradet. Perioder av torka kommer bli allt längre och kraftiga skyfall kommer bli vanligare. READ MORE

  5. 14. Deep Learning models for semantic segmentation of mammography screenings

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

    Author : Albert Bou; [2019]
    Keywords : ;

    Abstract : This work explores the performance of state-of-the-art semantic segmentation models on mammographic imagery. It does so by comparing several reference semantic segmentation deep learning models on a newly proposed medical dataset of mammograpgy screenings. READ MORE

  6. 15. GANtruth – a regularization method for unsupervised image-to-image translation

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

    Author : Sebastian Bujwid; [2018]
    Keywords : GAN; unsupervised image-to-image translation; deep learning;

    Abstract : In this work, we propose a novel and effective method for constraining the output space of the ill-posed problem of unsupervised image-to-image translation. We make the assumption that the environment of the source domain is known, and we propose to explicitly enforce preservation of the ground-truth labels on the images translated from the source to the target domain. READ MORE