Search Results for author: Jan Dirk Wegner

Found 28 papers, 15 papers with code

Mixture of Experts with Uncertainty Voting for Imbalanced Deep Regression Problems

no code implementations24 May 2023 Yuchang Jiang, Vivien Sainte Fare Garnot, Konrad Schindler, Jan Dirk Wegner

If training data are imbalanced, the learning is dominated by the densely covered regions of the target distribution, consequently, the learned regressor tends to exhibit poor performance in sparsely covered regions.

Probabilistic Deep Learning regression

FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

1 code implementation31 May 2022 Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz, Mina Rezaei, Bernd Bischl, Rodrigo Caye Daudt, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

We show that the idea can be extended to uncertainty quantification: by modulating the network activations of a single deep network with FiLM, one obtains a model ensemble with high diversity, and consequently well-calibrated estimates of epistemic uncertainty, with low computational overhead in comparison.

Multi-Task Learning Probabilistic Deep Learning

A high-resolution canopy height model of the Earth

no code implementations13 Apr 2022 Nico Lang, Walter Jetz, Konrad Schindler, Jan Dirk Wegner

The worldwide variation in vegetation height is fundamental to the global carbon cycle and central to the functioning of ecosystems and their biodiversity.

Decision Making Probabilistic Deep Learning +2

Towards a Collective Agenda on AI for Earth Science Data Analysis

1 code implementation11 Apr 2021 Devis Tuia, Ribana Roscher, Jan Dirk Wegner, Nathan Jacobs, Xiao Xiang Zhu, Gustau Camps-Valls

In the last years we have witnessed the fields of geosciences and remote sensing and artificial intelligence to become closer.

Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles

1 code implementation5 Mar 2021 Nico Lang, Nikolai Kalischek, John Armston, Konrad Schindler, Ralph Dubayah, Jan Dirk Wegner

NASA's Global Ecosystem Dynamics Investigation (GEDI) is a key climate mission whose goal is to advance our understanding of the role of forests in the global carbon cycle.

Probabilistic Deep Learning regression

PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds

1 code implementation ICLR 2021 Yujia Liu, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner

Next, the corners are linked with an exhaustive set of candidate edges, which is again pruned to obtain the final wireframe.

Crop mapping from image time series: deep learning with multi-scale label hierarchies

1 code implementation17 Feb 2021 Mehmet Ozgur Turkoglu, Stefano D'Aronco, Gregor Perich, Frank Liebisch, Constantin Streit, Konrad Schindler, Jan Dirk Wegner

The three-level label hierarchy is encoded in a convolutional, recurrent neural network (convRNN), such that for each pixel the model predicts three labels at different level of granularity.

Crop Classification General Classification +1

Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

1 code implementation4 Dec 2020 Nando Metzger, Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

We propose to use neural ordinary differential equations (NODEs) in combination with RNNs to classify crop types in irregularly spaced image sequences.

Crop Classification General Classification +1

Deep Active Learning in Remote Sensing for data efficient Change Detection

1 code implementation25 Aug 2020 Vít Růžička, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

We investigate active learning in the context of deep neural network models for change detection and map updating.

Active Learning Change Detection

Privileged Pooling: Better Sample Efficiency Through Supervised Attention

no code implementations20 Mar 2020 Andres C. Rodriguez, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner

We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets.

Image Classification

Geocoding of trees from street addresses and street-level images

no code implementations5 Feb 2020 Daniel Laumer, Nico Lang, Natalie van Doorn, Oisin Mac Aodha, Pietro Perona, Jan Dirk Wegner

We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching.

HistoNet: Predicting size histograms of object instances

1 code implementation11 Dec 2019 Kishan Sharma, Moritz Gold, Christian Zurbruegg, Laura Leal-Taixé, Jan Dirk Wegner

Our method results in an overall improvement in the count and size distribution prediction as compared to state-of-the-art instance segmentation method Mask R-CNN.

Instance Segmentation Semantic Segmentation

Gating Revisited: Deep Multi-layer RNNs That Can Be Trained

3 code implementations25 Nov 2019 Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.

Action Recognition In Videos Language Modelling +2

From Google Maps to a Fine-Grained Catalog of Street trees

no code implementations7 Oct 2019 Steve Branson, Jan Dirk Wegner, David Hall, Nico Lang, Konrad Schindler, Pietro Perona

We believe this is the first work to exploit publicly available image data for fine-grained tree mapping at city-scale, respectively over many thousands of trees.

Country-wide high-resolution vegetation height mapping with Sentinel-2

no code implementations30 Apr 2019 Nico Lang, Konrad Schindler, Jan Dirk Wegner

Sentinel-2 multi-spectral images collected over periods of several months were used to estimate vegetation height for Gabon and Switzerland.

Surface Reconstruction Vocal Bursts Intensity Prediction

Guided Super-Resolution as Pixel-to-Pixel Transformation

2 code implementations ICCV 2019 Riccardo de Lutio, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler

Guided super-resolution is a unifying framework for several computer vision tasks where the inputs are a low-resolution source image of some target quantity (e. g., perspective depth acquired with a time-of-flight camera) and a high-resolution guide image from a different domain (e. g., a grey-scale image from a conventional camera); and the target output is a high-resolution version of the source (in our example, a high-res depth map).


Topological Map Extraction from Overhead Images

no code implementations ICCV 2019 Zuoyue Li, Jan Dirk Wegner, Aurélien Lucchi

We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly.

Semantic Segmentation

Learning Aerial Image Segmentation from Online Maps

2 code implementations21 Jul 2017 Pascal Kaiser, Jan Dirk Wegner, Aurelien Lucchi, Martin Jaggi, Thomas Hofmann, Konrad Schindler

We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled, pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations.

General Classification Image Segmentation +1

Towards seamless multi-view scene analysis from satellite to street-level

no code implementations23 May 2017 Sébastien Lefèvre, Devis Tuia, Jan Dirk Wegner, Timothée Produit, Ahmed Samy Nassar

In this paper, we discuss and review how combined multi-view imagery from satellite to street-level can benefit scene analysis.

Change Detection object-detection +2

Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection

1 code implementation5 Dec 2016 Dimitrios Marmanis, Konrad Schindler, Jan Dirk Wegner, Silvano Galliani, Mihai Datcu, Uwe Stilla

We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries.

Boundary Detection Edge Detection +3

Cannot find the paper you are looking for? You can Submit a new open access paper.