6 papers
Fast and Compact Graph Cuts for the Boykov-Kolmogorov Algorithm
Christian Møller Mikkelstrup, Anders Bjorholm Dahl, Philip Bille +2
Computing a minimum - cut in a graph is a solution to a wide range of computer vision problems, and is often done using the Boykov-Kolmogorov (BK) algorithm. In this paper, w…
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
Oskar Kristoffersen, Alba Reinders Sánchez, Morten Rieger Hannemose +2
Geo-spatial analysis of our world benefits from a multimodal approach, as every single geographic location can be described in numerous ways (images from various viewpoints, textua…
Rethinking Uncertainty Quantification and Entanglement in Image Segmentation
Jakob Lønborg Christensen, Jakob Lønborg Christensen, Vedrana Andersen Dahl +3
Uncertainty quantification (UQ) is crucial in safety-critical applications such as medical image segmentation. Total uncertainty is typically decomposed into data-related aleatoric…
Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixels
Juan Miguel Valverde, Dim P. Papadopoulos, Rasmus Larsen +1
Standard deep learning models for image segmentation cannot guarantee topology accuracy, failing to preserve the correct number of connected components or structures. This, in turn…
TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracy
Juan Miguel Valverde, Motoya Koga, Nijihiko Otsuka +1
We present TopoMortar, a brick wall dataset that is the first dataset specifically designed to evaluate topology-focused image segmentation methods, such as topology loss functions…
Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentation
Juan Miguel Valverde, Maja Ãstergaard, Adrian Rodriguez-Palomo +4
Accurate segmentation of thin, tubular structures (e.g., blood vessels) is challenging for deep neural networks. These networks classify individual pixels, and even minor misclassi…