Sökning: "down-sampling"

Visar resultat 1 - 5 av 10 uppsatser innehållade ordet down-sampling.

1. 1. Enhancing Neural Network Accuracy on Long-Tailed Datasets through Curriculum Learning and Data Sorting

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Daniel Barreira; [2023]
   Nyckelord :Machine Learning; Neural Network; CORAL-framework; Long-Tailed Data; Imbalance Metrics; Teacher-Student models; Curriculum Learning; Training Scheme; Maskininlärning; Neuralt Nätverk; CORAL-ramverk; Long-Tailed Data; Imbalance Metrics; Teacher-Student modeler; Curriculum Learning; Tränings- scheman;

   Sammanfattning : In this paper, a study is conducted to investigate the use of Curriculum Learning as an approach to address accuracy issues in a neural network caused by training on a Long-Tailed dataset. The thesis problem is presented by a Swedish e-commerce company. LÄS MER

3. 2. Enhancement-basedSmall TargetDetection for InfraredImages

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

   Författare :Yang Hanqi; [2023]
   Nyckelord :Infrared Images; Small targets; Dilated Convolution; Infraröda bilder; Små mål; Dilaterad konvolution;

   Sammanfattning : Infrared small target detection is widely used in fields such as military and security. UNet, which is a classical semantic segmentation method proposed in 2015, has shown excellent performance and robustness. However, U-Net suffers from the problem of losing small targets in deep layers after multiple down-sampling operations. LÄS MER

4. 3. Dealing With Speckle Noise in Deep Neural Network Segmentation of Medical Ultrasound Images

   Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :Olmo Daniel; [2022]
   Nyckelord :Deep Learning; Ultrasound; Speckle Filtering; Medical Image Segmentation; U-Net; Wavelet Transfrom; Djupinlärning; Ultraljud; Specklefiltrering; Medicinsk bildsegmentering; U-Net; Wavelet transformation;

   Sammanfattning : Segmentation of ultrasonic images is a common task in healthcare that requires time and attention from healthcare professionals. Automation of medical image segmentation using deep learning solutions is fast growing field and has been shown to be capable of near human performance. LÄS MER

5. 4. GVT-BDNet : Convolutional Neural Network with Global Voxel Transformer Operators for Building Damage Assessment

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

   Författare :Leonardo Remondini; [2021]
   Nyckelord :Attention Operators; Convolutional Neural Networks CNNs ; Deep Learning; Building Damage Assessment; Generalizability; Global Voxel Transformer Operators GVTOs .; Attention Operators; Convolutional Neural Networks CNNs ; Deep Learning; Building Damage Assessment; Generalizability; Global Voxel Transformer Operators GVTOs .;

   Sammanfattning : Natural disasters strike anywhere, disrupting local communication and transportation infrastructure, making the process of assessing specific local damage difficult, dangerous, and slow. The goal of Building Damage Assessment (BDA) is to quickly and accurately estimate the location, cause, and severity of the damage to maximize the efficiency of rescuers and saved lives. LÄS MER

7. 5. Data Augmentation in Solving Data Imbalance Problems

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

   Författare :Jie Gao; [2020]
   Nyckelord :Data augmentation; Data imbalance; NLP; Deep learning; Comparison.; Dataförstoring; Data obalans; Textklassificering; Naturlig språkbehandling; Djup lärning.;

   Sammanfattning : This project mainly focuses on the various methods of solving data imbalance problems in the Natural Language Processing (NLP) field. Unbalanced text data is a common problem in many tasks especially the classification task, which leads to the model not being able to predict the minority class well. LÄS MER