214 citations
- University of OsloNO22 papers
- Forschungszentrum JülichDE16 papers
- Instituto Nacional de Pesquisas EspaciaisBR10 papers
- Jülich Aachen Research AllianceDE10 papers
- Petersburg Nuclear Physics InstituteRU10 papers
- Norwegian University of Science and TechnologyNO9 papers
- RWTH Aachen UniversityDE8 papers
- University of California, RiversideUS8 papers
- Simula Research LaboratoryNO7 papers
- SINTEFNO6 papers
- Karlsruhe Institute of TechnologyDE5 papers
- The University of Texas at AustinUS5 papers
5 papers · 1 filter
Semantic segmentation of forest stands using deep learning
Håkon Næss Sandum, Hans Ole Ørka, Oliver Tomic +2
Forest stands are the fundamental units in forest management inventories, silviculture, and financial analysis within operational forestry. Over the past two decades, a common meth…
SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning
William Heyden, Habib Ullah, M. Salman Siddiqui +1
Zero-Shot Learning (ZSL) presents the challenge of identifying categories not seen during training. This task is crucial in domains where it is costly, prohibited, or simply not fe…
An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
William Heyden, Habib Ullah, M. Salman Siddiqui +1
Zero-shot Learning (ZSL) classification categorizes or predicts classes (labels) that are not included in the training set (unseen classes). Recent works proposed different semanti…
Principal component-based image segmentation: a new approach to outline in vitro cell colonies
Delmon Arous, Stefan Schrunner, Ingunn Hanson +2
The in vitro clonogenic assay is a technique to study the ability of a cell to form a colony in a culture dish. By optical imaging, dishes with stained colonies can be scanned and…
Addressing Overfitting on Pointcloud Classification using Atrous XCRF
Hasan Asyari Arief, Ulf Geir Indahl, Geir-Harald Strand +1
Advances in techniques for automated classification of pointcloud data introduce great opportunities for many new and existing applications. However, with a limited number of label…