M. Sc. Lukas Rauch

AI for Computationally Intelligent Systems (AI4CIS)

E-Mail: lukas.rauch[at]uni-kassel[dot]de

Publikationen

[ 2025 ]
[ 2024 ]
[ 2023 ]
[ 2022 ]

2025[ to top ]

AudioProtoPNet: An interpretable deep learning model for bird sound classification. Heinrich, René; Rauch, Lukas; Sick, Bernhard; Scholz, Christoph. In Ecological Informatics, 87, bl 103081. Elsevier, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.
@article{heinrich2025audioprotopnet, abstract = {Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.}, author = {Heinrich, René and Rauch, Lukas and Sick, Bernhard and Scholz, Christoph}, journal = {Ecological Informatics}, keywords = {itegpub}, pages = 103081, publisher = {Elsevier}, title = {AudioProtoPNet: An interpretable deep learning model for bird sound classification}, volume = 87, year = 2025 }
%0 Journal Article %1 heinrich2025audioprotopnet %A Heinrich, René %A Rauch, Lukas %A Sick, Bernhard %A Scholz, Christoph %D 2025 %I Elsevier %J Ecological Informatics %P 103081 %R 10.1016/j.ecoinf.2025.103081 %T AudioProtoPNet: An interpretable deep learning model for bird sound classification %U https://www.sciencedirect.com/science/article/pii/S1574954125000901 %V 87 %X Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.

2024[ to top ]

The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification. Huseljic, Denis; Herde, Marek; Nagel, Yannick; Rauch, Lukas; Strimaitis, Paulius; Sick, Bernhard. In Transactions on Machine Learning Research. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.
@article{huseljic2024interplay, abstract = {Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.}, author = {Huseljic, Denis and Herde, Marek and Nagel, Yannick and Rauch, Lukas and Strimaitis, Paulius and Sick, Bernhard}, journal = {Transactions on Machine Learning Research}, keywords = {itegpub}, title = {The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification}, year = 2024 }
%0 Journal Article %1 huseljic2024interplay %A Huseljic, Denis %A Herde, Marek %A Nagel, Yannick %A Rauch, Lukas %A Strimaitis, Paulius %A Sick, Bernhard %D 2024 %J Transactions on Machine Learning Research %T The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification %U https://openreview.net/forum?id=KLBD13bsVl %X Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification. Huseljic, Denis; Hahn, Paul; Herde, Marek; Rauch, Lukas; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 280–296. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait in their evaluation. This paper introduces two methods to enhance \\textsc{Bait's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox.
@inproceedings{huseljic2024fast, abstract = {Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait}, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait}'s high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait} in their evaluation. This paper introduces two methods to enhance \\textsc{Bait}'s computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait} on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox}.}, author = {Huseljic, Denis and Hahn, Paul and Herde, Marek and Rauch, Lukas and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {280–296}, title = {Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification}, year = 2024 }
%0 Conference Paper %1 huseljic2024fast %A Huseljic, Denis %A Hahn, Paul %A Herde, Marek %A Rauch, Lukas %A Sick, Bernhard %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2024 %P 280--296 %R 10.1007/978-3-031-70368-3_17 %T Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification %X Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait in their evaluation. This paper introduces two methods to enhance \\textsc{Bait's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox.
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans. Herde, Marek; Huseljic, Denis; Rauch, Lukas; Sick, Bernhard. In Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks, bll 1–16. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.
@inproceedings{herde2024dopanim, abstract = {Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.}, author = {Herde, Marek and Huseljic, Denis and Rauch, Lukas and Sick, Bernhard}, booktitle = {Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks}, keywords = {itegpub}, pages = {1–16}, title = {dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans}, year = 2024 }
%0 Conference Paper %1 herde2024dopanim %A Herde, Marek %A Huseljic, Denis %A Rauch, Lukas %A Sick, Bernhard %B Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks %D 2024 %P 1--16 %T dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans %U https://openreview.net/forum?id=XOGosbxLrz %X Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.

2023[ to top ]

Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering. Aßenmacher, Matthias; Rauch, Lukas; Goschenhofer, Jann; Stephan, Andreas; Bischl, Bernd; Roth, Benjamin; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 65–73. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.
@inproceedings{assenmacher2023towards, abstract = {Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.}, author = {Aßenmacher, Matthias and Rauch, Lukas and Goschenhofer, Jann and Stephan, Andreas and Bischl, Bernd and Roth, Benjamin and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {65–73}, title = {Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering}, year = 2023 }
%0 Conference Paper %1 assenmacher2023towards %A Aßenmacher, Matthias %A Rauch, Lukas %A Goschenhofer, Jann %A Stephan, Andreas %A Bischl, Bernd %A Roth, Benjamin %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2023 %P 65--73 %T Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering %U https://ceur-ws.org/Vol-3470/paper7.pdf %X Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.
DADO – Low-Cost Query Strategies for Deep Active Design Optimization. Decke, Jens; Gruhl, Christian; Rauch, Lukas; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), bll 1611–1618. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.
@inproceedings{decke2023dado, abstract = {In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.}, author = {Decke, Jens and Gruhl, Christian and Rauch, Lukas and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1611–1618}, publisher = {IEEE}, title = {DADO – Low-Cost Query Strategies for Deep Active Design Optimization}, year = 2023 }
%0 Conference Paper %1 decke2023dado %A Decke, Jens %A Gruhl, Christian %A Rauch, Lukas %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2023 %I IEEE %P 1611--1618 %R 10.1109/ICMLA58977.2023.00244 %T DADO – Low-Cost Query Strategies for Deep Active Design Optimization %X In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers. Rauch, Lukas; Aßenmacher, Matthias; Huseljic, Denis; Wirth, Moritz; Bischl, Bernd; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 55–74. Springer, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.
@inproceedings{rauch2023activeglae, abstract = {Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.}, author = {Rauch, Lukas and Aßenmacher, Matthias and Huseljic, Denis and Wirth, Moritz and Bischl, Bernd and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {55–74}, publisher = {Springer}, title = {ActiveGLAE: A Benchmark for Deep Active Learning with Transformers}, year = 2023 }
%0 Conference Paper %1 rauch2023activeglae %A Rauch, Lukas %A Aßenmacher, Matthias %A Huseljic, Denis %A Wirth, Moritz %A Bischl, Bernd %A Sick, Bernhard %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2023 %I Springer %P 55--74 %R 10.1007/978-3-031-43412-9_4 %T ActiveGLAE: A Benchmark for Deep Active Learning with Transformers %U https://link.springer.com/chapter/10.1007/978-3-031-43412-9_4 %X Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.
Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers. Rauch, Lukas; Schwinger, Raphael; Wirth, Moritz; Sick, Bernhard; Tomforde, Sven; Scholz, Christoph. In Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI, bll 1–6. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.
@inproceedings{rauch2023active, abstract = {We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.}, author = {Rauch, Lukas and Schwinger, Raphael and Wirth, Moritz and Sick, Bernhard and Tomforde, Sven and Scholz, Christoph}, booktitle = {Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI}, keywords = {itegpub}, pages = {1–6}, title = {Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers}, year = 2023 }
%0 Conference Paper %1 rauch2023active %A Rauch, Lukas %A Schwinger, Raphael %A Wirth, Moritz %A Sick, Bernhard %A Tomforde, Sven %A Scholz, Christoph %B Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI %D 2023 %P 1--6 %T Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers %U https://arxiv.org/abs/2308.07121 %X We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.

2022[ to top ]

Predicting flow stress behavior of an AA7075 alloy using machine learning methods. Decke, Jens; Engelhardt, Anna; Rauch, Lukas; Degener, Sebastian; Sajjadifar, Seyedvahid; Scharifi, Emad; Steinhoff, Kurt; Niendorf, Thomas; Sick, Bernhard. In Crystals, 9(12), bll 1–19. MDPI, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^-1 to 0.1 s^-1 were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.
@article{decke2022predicting, abstract = {This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^{-1} to 0.1 s^{-1} were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.}, author = {Decke, Jens and Engelhardt, Anna and Rauch, Lukas and Degener, Sebastian and Sajjadifar, Seyedvahid and Scharifi, Emad and Steinhoff, Kurt and Niendorf, Thomas and Sick, Bernhard}, journal = {Crystals}, keywords = {itegpub}, number = 12, pages = {1–19}, publisher = {MDPI}, title = {Predicting flow stress behavior of an AA7075 alloy using machine learning methods}, volume = 9, year = 2022 }
%0 Journal Article %1 decke2022predicting %A Decke, Jens %A Engelhardt, Anna %A Rauch, Lukas %A Degener, Sebastian %A Sajjadifar, Seyedvahid %A Scharifi, Emad %A Steinhoff, Kurt %A Niendorf, Thomas %A Sick, Bernhard %D 2022 %I MDPI %J Crystals %N 12 %P 1--19 %R 10.3390/cryst12091281 %T Predicting flow stress behavior of an AA7075 alloy using machine learning methods %U https://www.mdpi.com/2073-4352/12/9/1281 %V 9 %X This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^-1 to 0.1 s^-1 were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.
Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources. Rauch, Lukas; Huseljic, Denis; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, bll 27–42. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.
@inproceedings{rauch2022enhancing, abstract = {One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.}, author = {Rauch, Lukas and Huseljic, Denis and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {27–42}, title = {Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources}, year = 2022 }
%0 Conference Paper %1 rauch2022enhancing %A Rauch, Lukas %A Huseljic, Denis %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2022 %P 27--42 %T Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources %U http://ceur-ws.org/Vol-3259/ialatecml_paper3.pdf %X One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.