387 citations · 449 across the 17 of their papers we have counts for
19 papers
From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps
Ghjulia Sialelli, Robin Young, Yuchang Jiang +9
Recent years have seen a rapid expansion in the production of large-scale geospatial maps derived from Earth observation (EO) data, driven largely by advances in machine learning (…
Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning
Richard Lindholm, Oscar Marklund, Olof Mogren +1
The vast amounts of audio data collected in Sound Event Detection (SED) applications require efficient annotation strategies to enable supervised learning. Manual labeling is expen…
The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time
John Martinsson, Tuomas Virtanen, Maria Sandsten +1
Accurate labels are critical for deriving robust machine learning models. Labels are used to train supervised learning models and to evaluate most machine learning paradigms. In th…
Flexible SE(2) graph neural networks with applications to PDE surrogates
Maria Bånkestad, Olof Mogren, Aleksis Pirinen
This paper presents a novel approach for constructing graph neural networks equivariant to 2D rotations and translations and leveraging them as PDE surrogates on non-gridded domain…
Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning
Martin Willbo, Aleksis Pirinen, John Martinsson +3
Land cover classification and change detection are two important applications of remote sensing and Earth observation (EO) that have benefited greatly from the advances of deep lea…
From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning
John Martinsson, Olof Mogren, Maria Sandsten +1
We propose an adaptive change point detection method (A-CPD) for machine guided weak label annotation of audio recording segments. The goal is to maximize the amount of information…