Search Results for author: Christian Igel

Found 37 papers, 15 papers with code

Predicting urban tree cover from incomplete point labels and limited background information

no code implementations20 Nov 2023 HUI ZHANG, Ankit Kariryaa, Venkanna Babu Guthula, Christian Igel, Stefan Oehmcke

This paper studies how to combine accurate point labels of urban trees along streets with crowd-sourced annotations from an open geographic database to delineate city trees in remote sensing images, a task which is challenging even for humans.

Semantic Segmentation

Benchmarking Individual Tree Mapping with Sub-meter Imagery

no code implementations14 Nov 2023 Dimitri Gominski, Ankit Kariryaa, Martin Brandt, Christian Igel, Sizhuo Li, Maurice Mugabowindekwe, Rasmus Fensholt

There is a rising interest in mapping trees using satellite or aerial imagery, but there is no standardized evaluation protocol for comparing and enhancing methods.

Benchmarking Segmentation

Familiarity-Based Open-Set Recognition Under Adversarial Attacks

no code implementations8 Nov 2023 Philip Enevoldsen, Christian Gundersen, Nico Lang, Serge Belongie, Christian Igel

Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications.

Open Set Learning

Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI

no code implementations5 Sep 2023 Dustin Wright, Christian Igel, Gabrielle Samuel, Raghavendra Selvan

The solution lionized by both industry and the ML community to improve the environmental sustainability of ML is to increase the efficiency with which ML systems operate in terms of both compute and energy consumption.

Smooth Monotonic Networks

no code implementations1 Jun 2023 Christian Igel

The resulting smooth min-max (SMM) network module inherits the asymptotic approximation properties from the MM architecture.

Decision Making Fairness

BuildSeg: A General Framework for the Segmentation of Buildings

no code implementations15 Jan 2023 Lei LI, Tianfang Zhang, Stefan Oehmcke, Fabian Gieseke, Christian Igel

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.

Self-Supervised Speech Representation Learning: A Review

no code implementations21 May 2022 Abdelrahman Mohamed, Hung-Yi Lee, Lasse Borgholt, Jakob D. Havtorn, Joakim Edin, Christian Igel, Katrin Kirchhoff, Shang-Wen Li, Karen Livescu, Lars Maaløe, Tara N. Sainath, Shinji Watanabe

Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Remember to correct the bias when using deep learning for regression!

no code implementations30 Mar 2022 Christian Igel, Stefan Oehmcke

We suggest to adjust the bias of the machine learning model after training as a default postprocessing step, which efficiently solves the problem.


Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass

no code implementations21 Dec 2021 Stefan Oehmcke, Lei LI, Katerina Trepekli, Jaime Revenga, Thomas Nord-Larsen, Fabian Gieseke, Christian Igel

Quantification of forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures.

Management regression

Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

no code implementations29 Nov 2021 Lasse Borgholt, Jakob Drachmann Havtorn, Mostafa Abdou, Joakim Edin, Lars Maaløe, Anders Søgaard, Christian Igel

We compare learned speech features from wav2vec 2. 0, state-of-the-art ASR transcripts, and the ground truth text as input for a novel speech-based named entity recognition task, a cardiac arrest detection task on real-world emergency calls and two existing SLU benchmarks.

Ranked #7 on Spoken Language Understanding on Fluent Speech Commands (using extra training data)

Automatic Speech Recognition Automatic Speech Recognition (ASR) +8

Information Bottleneck: Exact Analysis of (Quantized) Neural Networks

1 code implementation ICLR 2022 Stephan Sloth Lorenzen, Christian Igel, Mads Nielsen

In this setting, we observed a fitting phase for all layers and a compression phase for the output layer in all experiments; the compression in the hidden layers was dependent on the type of activation function.

Do End-to-End Speech Recognition Models Care About Context?

no code implementations17 Feb 2021 Lasse Borgholt, Jakob Drachmann Havtorn, Željko Agić, Anders Søgaard, Lars Maaløe, Christian Igel

We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input.

Language Modelling speech-recognition +1

On Scaling Contrastive Representations for Low-Resource Speech Recognition

no code implementations1 Feb 2021 Lasse Borgholt, Tycho Max Sylvester Tax, Jakob Drachmann Havtorn, Lars Maaløe, Christian Igel

We explore the performance of such systems without fine-tuning by training a state-of-the-art speech recognizer on the fixed representations from the computationally demanding wav2vec 2. 0 framework.

Self-Supervised Learning speech-recognition +1

Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts

1 code implementation18 Jan 2021 Svetlana Kutuzova, Oswin Krause, Douglas McCloskey, Mads Nielsen, Christian Igel

Multimodal generative models should be able to learn a meaningful latent representation that enables a coherent joint generation of all modalities (e. g., images and text).

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

1 code implementation NeurIPS 2020 Steffen Czolbe, Oswin Krause, Ingemar Cox, Christian Igel

To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.


On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions

no code implementations26 Jun 2020 Kai Brügge, Asja Fischer, Christian Igel

We propose a modified Metropolis transition operator that behaves almost always identically to the standard Metropolis operator and prove that it ensures irreducibility and convergence to the limiting distribution in the multivariate binary case with fixed-order updates.

A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model

1 code implementation26 Jun 2020 Steffen Czolbe, Oswin Krause, Ingemar Cox, Christian Igel

To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity.


Label-similarity Curriculum Learning

no code implementations ECCV 2020 Urun Dogan, Aniket Anand Deshmukh, Marcin Machura, Christian Igel

We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label representation.

Classification General Classification +2

One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation

2 code implementations5 Nov 2019 Mathias Perslev, Erik Bjørnager Dam, Akshay Pai, Christian Igel

The system relies on multi-planar data augmentation which facilitates the application of a single 2D architecture based on the familiar U-Net.

Data Augmentation Image Segmentation +5

Knowledge distillation for semi-supervised domain adaptation

no code implementations16 Aug 2019 Mauricio Orbes-Arteaga, Jorge Cardoso, Lauge Sørensen, Christian Igel, Sebastien Ourselin, Marc Modat, Mads Nielsen, Akshay Pai

As a result, their performance is significantly lower on data from unseen sources compared to the performance on data from the same source as the training data.

Domain Adaptation Knowledge Distillation +1

The Liver Tumor Segmentation Benchmark (LiTS)

6 code implementations13 Jan 2019 Patrick Bilic, Patrick Christ, Hongwei Bran Li, Eugene Vorontsov, Avi Ben-Cohen, Georgios Kaissis, Adi Szeskin, Colin Jacobs, Gabriel Efrain Humpire Mamani, Gabriel Chartrand, Fabian Lohöfer, Julian Walter Holch, Wieland Sommer, Felix Hofmann, Alexandre Hostettler, Naama Lev-Cohain, Michal Drozdzal, Michal Marianne Amitai, Refael Vivantik, Jacob Sosna, Ivan Ezhov, Anjany Sekuboyina, Fernando Navarro, Florian Kofler, Johannes C. Paetzold, Suprosanna Shit, Xiaobin Hu, Jana Lipková, Markus Rempfler, Marie Piraud, Jan Kirschke, Benedikt Wiestler, Zhiheng Zhang, Christian Hülsemeyer, Marcel Beetz, Florian Ettlinger, Michela Antonelli, Woong Bae, Míriam Bellver, Lei Bi, Hao Chen, Grzegorz Chlebus, Erik B. Dam, Qi Dou, Chi-Wing Fu, Bogdan Georgescu, Xavier Giró-i-Nieto, Felix Gruen, Xu Han, Pheng-Ann Heng, Jürgen Hesser, Jan Hendrik Moltz, Christian Igel, Fabian Isensee, Paul Jäger, Fucang Jia, Krishna Chaitanya Kaluva, Mahendra Khened, Ildoo Kim, Jae-Hun Kim, Sungwoong Kim, Simon Kohl, Tomasz Konopczynski, Avinash Kori, Ganapathy Krishnamurthi, Fan Li, Hongchao Li, Junbo Li, Xiaomeng Li, John Lowengrub, Jun Ma, Klaus Maier-Hein, Kevis-Kokitsi Maninis, Hans Meine, Dorit Merhof, Akshay Pai, Mathias Perslev, Jens Petersen, Jordi Pont-Tuset, Jin Qi, Xiaojuan Qi, Oliver Rippel, Karsten Roth, Ignacio Sarasua, Andrea Schenk, Zengming Shen, Jordi Torres, Christian Wachinger, Chunliang Wang, Leon Weninger, Jianrong Wu, Daguang Xu, Xiaoping Yang, Simon Chun-Ho Yu, Yading Yuan, Miao Yu, Liping Zhang, Jorge Cardoso, Spyridon Bakas, Rickmer Braren, Volker Heinemann, Christopher Pal, An Tang, Samuel Kadoury, Luc Soler, Bram van Ginneken, Hayit Greenspan, Leo Joskowicz, Bjoern Menze

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018.

Benchmarking Computed Tomography (CT) +3

On PAC-Bayesian Bounds for Random Forests

1 code implementation23 Oct 2018 Stephan Sloth Lorenzen, Christian Igel, Yevgeny Seldin

This effect provides a significant boost in performance when the errors are independent or negatively correlated, but when the correlations are strong the advantage from taking the majority vote is small.

Generalization Bounds

PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation

no code implementations3 Oct 2018 Mauricio Orbes Arteaga, Lauge Sørensen, M. Jorge Cardoso, Marc Modat, Sebastien Ourselin, Stefan Sommer, Mads Nielsen, Christian Igel, Akshay Pai

For proper generalization performance of convolutional neural networks (CNNs) in medical image segmentation, the learnt features should be invariant under particular non-linear shape variations of the input.

Image Segmentation Medical Image Segmentation +1

Training Big Random Forests with Little Resources

1 code implementation18 Feb 2018 Fabian Gieseke, Christian Igel

Without access to large compute clusters, building random forests on large datasets is still a challenging problem.

CMA-ES with Optimal Covariance Update and Storage Complexity

no code implementations NeurIPS 2016 Oswin Krause, Dídac Rodríguez Arbonès, Christian Igel

The covariance matrix adaptation evolution strategy (CMA-ES) is arguably one of the most powerful real-valued derivative-free optimization algorithms, finding many applications in machine learning.

A Strongly Quasiconvex PAC-Bayesian Bound

no code implementations19 Aug 2016 Niklas Thiemann, Christian Igel, Olivier Wintenberger, Yevgeny Seldin

We propose a new PAC-Bayesian bound and a way of constructing a hypothesis space, so that the bound is convex in the posterior distribution and also convex in a trade-off parameter between empirical performance of the posterior distribution and its complexity.

Bigger Buffer k-d Trees on Multi-Many-Core Systems

1 code implementation9 Dec 2015 Fabian Gieseke, Cosmin Eugen Oancea, Ashish Mahabal, Christian Igel, Tom Heskes

A buffer k-d tree is a k-d tree variant for massively-parallel nearest neighbor search.


Sacrificing information for the greater good: how to select photometric bands for optimal accuracy

1 code implementation17 Nov 2015 Kristoffer Stensbo-Smidt, Fabian Gieseke, Christian Igel, Andrew Zirm, Kim Steenstrup Pedersen

This study promotes a feature selection algorithm, which selects the most informative magnitudes and colours for a given task of estimating physical quantities from photometric data alone.

BIG-bench Machine Learning feature selection +1

Population-Contrastive-Divergence: Does Consistency help with RBM training?

no code implementations6 Oct 2015 Oswin Krause, Asja Fischer, Christian Igel

Compared to CD, it leads to a consistent estimate and may have a significantly lower bias.

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