Essays about: "DenseNet"

Showing result 11 - 14 of 14 essays containing the word DenseNet.

  1. 11. Evaluation of Instance Segmentation Methods in the Context of Construction Waste

    University essay from Lunds universitet/Matematik LTH

    Author : Emil Sandelin; [2021]
    Keywords : Image analysis; Instance segmentation; Mask RCNN; SOLOv2; Mathematics and Statistics;

    Abstract : With the progress made within the field of computer vision the last few years, it is starting to become possible to perform instance segmentation in real time with relatively cheap hardware. This paper's main purpose is to investigate different methods of instance segmentation in the specific case of segmenting construction waste with only a single class. READ MORE

  3. 12. Avoiding Catastrophic Forgetting in Continual Learning through Elastic Weight Consolidation

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

    Author : Anton Evilevitch; Robert Ingram; [2021]
    Keywords : Image classification; DenseNet; Elastic Weight Consolidation; Catastrophic Forgetting; CIFAR100; Bildklassifiering; DenseNet; Elastic Weight Consolidation; Catastrophic Forgetting; CIFAR100;

    Abstract : Image classification is an area of computer science with many areas of application. One key issue with using Artificial Neural Networks (ANN) for image classification is the phenomenon of Catastrophic Forgetting when training tasks sequentially (i.e Continual Learning). READ MORE

  4. 13. Monocular Depth Prediction in Deep Neural Networks

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

    Author : Guanqian Tang; [2019]
    Keywords : Convolutional neural networks; monocular depth prediction; ResNet; DenseNet; ; Konvolutional neurala nätverk; monokulär djupförutsägelse; ResNet; DenseNet; ;

    Abstract : With the development of artificial neural network (ANN), it has been introduced in more and more computer vision tasks. Convolutional neural networks (CNNs) are widely used in object detection, object tracking, and semantic segmentation, achieving great performance improvement than traditional algorithms. READ MORE

  5. 14. Semantic Segmentation of Iron Ore Pellets with Neural Networks

    University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Author : Terese Svensson; [2019]
    Keywords : Convolutional Neural Networks; Iron Ore Pellets; Semantic Segmentation;

    Abstract : This master’s thesis evaluates five existing Convolutional Neural Network (CNN) models for semantic segmentation of optical microscopy images of iron ore pellets. The models are PSPNet, FC-DenseNet, DeepLabv3+, BiSeNet and GCN. READ MORE