SwePub
Sök i SwePub databas

  Extended search

Träfflista för sökning "LAR1:ltu ;mspu:(publicationother)"

Search: LAR1:ltu > Other publication

  • Result 1-10 of 1443
Sort/group result
   
EnumerationReferenceCoverFind
1.
  •  
2.
  • Abid, Nosheen, et al. (author)
  • Multi-UCL: Multi-class Unsupervised Curriculum Learning for Image Scene Classification : Case Study: Earth Observation
  • Other publication (other academic/artistic)abstract
    • The effective training of supervised deep learning models requires the labeling of extensive datasets, a process that is often costly and labor-intensive. Such models also face significant challenges with overfitting on the training data with true labels, leading to suboptimal performance on new datasets with slight variations in capturing sources or regions. This paper introduces Multi-class Unsupervised Curriculum Learning (Multi-class UCL), a novel deep learning framework. We demonstrate the effectiveness of this framework on the  case study of land use and cover classification that bypasses the need for labeled data, thereby improving adaptability across different datasets. Multi-class UCL leverages pseudo-labels generated from a clustering technique to train the model and incorporates a selection process that ensures an equal representation of samples from each cluster, addressing the issue of class imbalance. The study evaluates the effectiveness of Multi-class UCL through comprehensive experiments on four diverse publicly available datasets: EuroSAT, SAT-6, RSSCN7, and UCMerced. These datasets have varying resolutions, come from different capturing sources, and encompass different geographical areas.The results demonstrate that the framework effectively learns and generalizes important features from the data, showing superior adaptability and performance across various datasets compared to traditional supervised models.
  •  
3.
  • Abid, Nosheen, et al. (author)
  • UCL: Unsupervised Curriculum Learning for Image Classification
  • Other publication (pop. science, debate, etc.)abstract
    • In many real-world applications of computer vision complex domains, such as medical diagnostics and document analysis, the lack of labeled data often limits the effectiveness of traditional deep learning models. This study addresses these challenges by enhancing Unsupervised Curriculum Learning (UCL), a deep learning framework that automatically discovers meaningful patterns without the need for labeled data. Originally designed for remote sensing imagery, UCL has been expanded in this work to improve classification performance in a variety of domain-specific applications. UCL integrates a convolutional neural network, clustering algorithms, and selection techniques to classify images unsupervised. We introduce key improvements, such as spectral clustering, outlier detection, and dimensionality reduction, to boost the framework’s accuracy. Experimental results demonstrate significant performance gains, with F1-scores increasing from 68% to 94% on a three-class subset of the CIFAR-10 dataset and from 68% to 75% on a five-class subset. The updated UCL also achieved F1-scores of 85% in medical diagnosis, 82% in scene recognition, and 62% in historical document classification. These findings underscore the potential of UCL in complex real-world applications and point to areas where further advancements are needed to maximize its utility across diverse fields.
  •  
4.
  • Abrahamsson, Kenneth (author)
  • Efterord
  • 2007
  • Other publication (pop. science, debate, etc.)
  •  
5.
  • Abrahamsson, Kenneth (author)
  • Efterord
  • 2006
  • Other publication (pop. science, debate, etc.)
  •  
6.
  • Abrahamsson, Kenneth (author)
  • Förord
  • 2007
  • Other publication (pop. science, debate, etc.)
  •  
7.
  • Abrahamsson, Lena (author)
  • Några skrivtips
  • 2007
  • Other publication (pop. science, debate, etc.)
  •  
8.
  • Abrahamsson, Lena, et al. (author)
  • Project: Cracks in the workers’ collective – windows for change towards gender equal mining workplaces
  • 2014
  • Other publication (pop. science, debate, etc.)abstract
    • Forskningsprojektet ”Cracks in the workers’ collective – windows for change towards gender equal mining workplaces” handlar om könskonstruktioner i arbetarkollektivets förändringar inom gruvindustrin (mansdominerade arbetsplatser). Projektet pågår 2015-2017 med finansiering från FORTE (2.700.000 kr). I projektet medverkar Lena Abrahamsson, Ylva Fältholm (proj.ledare), Eira Andersson och doktorand Lisa Andersson.
  •  
9.
  •  
10.
  •  
Skapa referenser, mejla, bekava och länka
  • Result 1-10 of 1443
Type of publication
other publication  (1443)Undo refine
artistic work (63)
Type of content
pop. science, debate, etc. (919)
other academic/artistic (496)
peer-reviewed (9)
Author/Editor
Foster, Tim (65)
Parida, Aditya (46)
Abrahamsson, Lena (33)
Unander-Scharin, Åsa (25)
Awad, Ali Ismail (23)
Berglund, Knut-Erlan ... (23)
show more...
Ekman, Jonas (22)
Andersson, Karl (21)
Stage, Jesper (21)
Larsson, Tobias (21)
Melander-Wikman, Ani ... (18)
Jullander, Sverker (17)
Parnes, Peter (16)
Viklander, Maria (15)
Liwicki, Marcus (13)
Christakopoulos, Pau ... (13)
Larsson, Agneta (13)
Lassinantti, Josefin (13)
Allard, Christina (11)
Hansson, Johan (11)
Grafström, Jonas, 19 ... (11)
Veljkovic, Milan (11)
Lidelöw, Helena (11)
Fältholm, Ylva (10)
Lindberg, Malin (10)
Johansson, Jeaneth (10)
Delsing, Jerker (10)
Alakangas, Lena (10)
Greberg, Jenny (10)
Stehn, Lars (10)
Malmström, Malin (10)
Segerstedt, Anders (9)
Grane, Camilla (9)
Ericson, Åsa (9)
Rova, Ulrika (9)
Engström, Åsa (9)
Emami, Nazanin (9)
Elfgren, Lennart (9)
Wennberg, Paula (9)
Andersson, Ninnie (9)
Bodin, Ulf (9)
Weihed, Pär, 1959- (9)
Weihed, Pär (8)
Olsson, Malin (8)
Kajberg, Jörgen (8)
Johansson, Jan (8)
Etherden, Nicholas (8)
Schelén, Olov (8)
Thurley, Matthew (8)
Thorgren, Sara (8)
show less...
University
Luleå University of Technology (1443)
Uppsala University (17)
Umeå University (11)
Blekinge Institute of Technology (2)
Swedish University of Agricultural Sciences (2)
Mälardalen University (1)
show more...
RISE (1)
Högskolan Dalarna (1)
show less...
Language
English (817)
Swedish (614)
Finnish (6)
Latin (3)
Italian (2)
Slovenian (1)
Research subject (UKÄ/SCB)
Engineering and Technology (664)
Social Sciences (307)
Natural sciences (180)
Humanities (137)
Medical and Health Sciences (84)
Agricultural Sciences (1)

Year

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view