Essays about: "Semantisk Segmentering"

Showing result 11 - 15 of 57 essays containing the words Semantisk Segmentering.

1. 11. Mixed Precision Quantization for Computer Vision Tasks in Autonomous Driving

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

   Author : Sri Janani Rengarajan; [2022]
   Keywords : Quantization; Neural Networks; Quantization Aware Training; Mixed precision; Semantic segmentation; Hessian; Kvantisering; Neurala nätverk; Kvantiseringsmedveten träning; Blandad precision; Semantisk segmentering; Hessian;

   Abstract : Quantization of Neural Networks is popular technique for adopting computation intensive Deep Learning applications to edge devices. In this work, low bit mixed precision quantization of FPN-Resnet18 model trained for the task of semantic segmentation is explored using Cityscapes and Arriver datasets. READ MORE

3. 12. Online Unsupervised Domain Adaptation

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

   Author : Theodoros Panagiotakopoulos; [2022]
   Keywords : Unsupervised Domain Adaptation; Continual Learning; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantic Segmentation; Transfer Learning; Online Learning; Unsupervised Domain Adaptation; Kontinuerligt lärande; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantisk Segmentering; Transfer Learning; Online Learning;

   Abstract : Deep Learning models have seen great application in demanding tasks such as machine translation and autonomous driving. However, building such models has proved challenging, both from a computational perspective and due to the requirement of a plethora of annotated data. READ MORE

4. 13. News article segmentation using multimodal input : Using Mask R-CNN and sentence transformers

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

   Author : Gustav Henning; [2022]
   Keywords : Historical newspapers; Image segmentation; Multimodal learning; Deep learning; Digital humanities; Mask R-CNN; Historiska tidningar; Bildsegmentering; Multimodal inlärning; Djupinlärning; Digital humaniora; Mask R-CNN;

   Abstract : In this century and the last, serious efforts have been made to digitize the content housed by libraries across the world. In order to open up these volumes to content-based information retrieval, independent elements such as headlines, body text, bylines, images and captions ideally need to be connected semantically as article-level units. READ MORE

5. 14. Screw Hole Detection in Industrial Products using Neural Network based Object Detection and Image Segmentation : A Study Providing Ideas for Future Industrial Applications

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

   Author : Jakob Melki; [2022]
   Keywords : Artificial intelligence AI ; Automated assembly and disassembly; Computer vision; Machine learning; Neural networks; Object detection; Screw hole detection; Semantic segmentation; Artificiell intelligens AI ; Automatiserad montering och demontering; Datorseende; Maskininlärning; Neurala nätverk; Objekt detektering; Skruvhålsdetektering; Semantisk segmentering;

   Abstract : This project is about screw hole detection using neural networks for automated assembly and disassembly. In a lot of industrial companies, such as Ericsson AB, there are products such as radio units or filters that have a lot of screw holes. READ MORE

6. 15. Deep Learning Semantic Segmentation of 3D Point Cloud Data from a Photon Counting LiDAR

   University essay from Linköpings universitet/Datorseende

   Author : Caspian Süsskind; [2022]
   Keywords : Deep Learning; Machine Learning; Computer vision; Semantic Segmentation; Photon Counting LiDAR; LiDAR; Point Cloud; 3D Data; Point Cloud Segmentation; Point Classification; Convolutional Neural Network; CNN; SPVCNN; Djupinlärning; LiDAR; fotonräknande LiDAR; semantisk segmentering; datorseende; punktmoln; maskininlärning;

   Abstract : Deep learning has shown to be successful on the task of semantic segmentation of three-dimensional (3D) point clouds, which has many interesting use cases in areas such as autonomous driving and defense applications. A common type of sensor used for collecting 3D point cloud data is Light Detection and Ranging (LiDAR) sensors. READ MORE