← Search

Vedrana A Dahl

3 accepted papers

2024

BugNIST - a Large Volumetric Dataset for Detection under Domain Shift

ECCV 2024poster

"Domain shift significantly influences the performance of deep learning algorithms, particularly for object detection within volumetric 3D images. Annotated training data is essential for deep learning-based object detection. However, annotating densely packed objects is time-consuming and costly. I…

Cited by 1SourcePDFScholar
2021

Faster Multi-Object Segmentation Using Parallel Quadratic Pseudo-Boolean Optimization

ICCV 2021poster

We introduce a parallel version of the Quadratic Pseudo-Boolean Optimization (QPBO) algorithm for solving binary optimization tasks, such as image segmentation. The original QPBO implementation by Kolmogorov and Rother relies on the Boykov-Kolmogorov (BK) maxflow/mincut algorithm and performs well f…

Cited by 3PDFScholar
2020

Sparse Layered Graphs for Multi-Object Segmentation

CVPR 2020poster

We introduce the novel concept of a Sparse Layered Graph (SLG) for s-t graph cut segmentation of image data. The concept is based on the widely used Ishikawa layered technique for multi-object segmentation, which allows explicit object interactions, such as containment and exclusion with margins. Ho…

Cited by 11PDFcodeScholar