6 citations · 16 across the 17 of their papers we have counts for
18 papers
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
Ashwin Nedungadi, Stefan Oehmcke, Stefan Lüdtke
Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal r…
Uncertainty-aware tree height change regression
Max Gaber, Dimitri Gominski, Jaime C. Revenga +3
Monitoring canopy height change is essential for understanding carbon sinks and forest dynamics. Remote sensing enables consistent, large-scale observations of such changes, increa…
Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
Feyza Eksen, Stefan Oehmcke, Stefan Lüdtke
Accurate sensor placement is critical for modeling spatio-temporal systems such as environmental and climate processes. Neural Processes (NPs), particularly Convolutional Condition…
Boosted Trees on a Diet: Compact Models for Resource-Constrained Devices
Nina Herrmann, Jan Stenkamp, Benjamin Karic +2
Deploying machine learning models on compute-constrained devices has become a key building block of modern IoT applications. In this work, we present a compression scheme for boost…
Multimodal classification of forest biodiversity potential from 2D orthophotos and 3D airborne laser scanning point clouds
Simon B. Jensen, Stefan Oehmcke, Andreas Møgelmose +4
Assessment of forest biodiversity is crucial for ecosystem management and conservation. While traditional field surveys provide high-quality assessments, they are labor-intensive a…
Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment
Venkanna Babu Guthula, Stefan Oehmcke, Remigio Chilaule +5
As low-quality housing and in particular certain roof characteristics are associated with an increased risk of malaria, classification of roof types based on remote sensing imagery…
MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
Vishal Nedungadi, Ankit Kariryaa, Stefan Oehmcke +3
The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair da…
Tree Counting by Bridging 3D Point Clouds with Imagery
Lei Li, Tianfang Zhang, Zhongyu Jiang +6
Accurate and consistent methods for counting trees based on remote sensing data are needed to support sustainable forest management, assess climate change mitigation strategies, an…
Predicting urban tree cover from incomplete point labels and limited background information
Hui Zhang, Ankit Kariryaa, Venkanna Babu Guthula +2
Trees inside cities are important for the urban microclimate, contributing positively to the physical and mental health of the urban dwellers. Despite their importance, often only…
BuildSeg: A General Framework for the Segmentation of Buildings
Lei Li, Tianfang Zhang, Stefan Oehmcke +2
Building segmentation from aerial images and 3D laser scanning (LiDAR) is a challenging task due to the diversity of backgrounds, building textures, and image quality. While curren…
LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing
Tianfang Zhang, Lei Li, Christian Igel +3
Deep unfolding networks (DUNs) have proven to be a viable approach to compressive sensing (CS). In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural ima…
Remember to correct the bias when using deep learning for regression!
Christian Igel, Stefan Oehmcke
When training deep learning models for least-squares regression, we cannot expect that the training error residuals of the final model, selected after a fixed training time or base…
Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass
Stefan Oehmcke, Lei Li, Katerina Trepekli +4
Quantification of forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures. The knowledge is needed, e.g., for local fore…
Attentional Feature Fusion
Yimian Dai, Fabian Gieseke, Stefan Oehmcke +2
Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations…
Attention as Activation
Yimian Dai, Stefan Oehmcke, Fabian Gieseke +2
Activation functions and attention mechanisms are typically treated as having different purposes and have evolved differently. However, both concepts can be formulated as a non-lin…
Magnitude and Uncertainty Pruning Criterion for Neural Networks
Vinnie Ko, Stefan Oehmcke, Fabian Gieseke
Neural networks have achieved dramatic improvements in recent years and depict the state-of-the-art methods for many real-world tasks nowadays. One drawback is, however, that many…
Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data
Stefan Oehmcke, Christoffer Thrysøe, Andreas Borgstad +3
Massive amounts of satellite data have been gathered over time, holding the potential to unveil a spatiotemporal chronicle of the surface of Earth. These data allow scientists to i…
Input Selection for Bandwidth-Limited Neural Network Inference
Stefan Oehmcke, Fabian Gieseke
Data are often accommodated on centralized storage servers. This is the case, for instance, in remote sensing and astronomy, where projects produce several petabytes of data every…