Lukas Rauch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lukas Rauch has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Bernhard Sick
University of Kassel
7 shared publications - Denis Huseljic
University of Kassel
3 shared publications - Moritz Wirth
IES University of Kassel
3 shared publications - Bernd Bischl
LMU Munich
2 shared publications - Marek Herde
University of Kassel, Germany
2 shared publications - Matthias Aßenmacher
Department of Statistics LMU Munich
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 27 April 2026
- Published by Elsevier in Ecological Informatics
- Vol. 96
Foundation models for bioacoustics – A comparative review
- 27 April 2026
- Published by Elsevier in Ecological Informatics
- Vol. 96
Top Cited PapersOpen AccessFoundation models for bioacoustics – A comparative review
- Open Access
BAT: Better Audio Transformer Guided by Convex Gated Probing
Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as fine-tuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on fine-tuning because simple probing fails to unlock their full potential and alters their rankings when competing for SOTA on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards reliable and reproducible methods. We introduce Convex Gated Probing (CGP), a prototype-based method that drastically closes the gap between fine-tuning and probing in audio. CGP efficiently utilizes all frozen layers via a gating mechanism and exposes the location of latent task-relevant information. Guided by CGP, we rework the entire SSL pipeline of current SOTA audio models that use legacy implementations of prior SSL methods. By refining data preprocessing, model architecture, and pre-training recipe, we introduce Better Audio Transformer (BAT), and establish new SOTA on audio benchmarks.
Open AccessBAT: Better Audio Transformer Guided by Convex Gated Probing
Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as fine-tuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on fine-tuning because simple probing fails to unlock their full potential and alters their rankings when competing for SOTA on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards reliable and reproducible methods. We introduce Convex Gated Probing (CGP), a prototype-based method that drastically closes the gap between fine-tuning and probing in audio. CGP efficiently utilizes all frozen layers via a gating mechanism and exposes the location of latent task-relevant information. Guided by CGP, we rework the entire SSL pipeline of current SOTA audio models that use legacy implementations of prior SSL methods. By refining data preprocessing, model architecture, and pre-training recipe, we introduce Better Audio Transformer (BAT), and establish new SOTA on audio benchmarks.
- Open Access
- 4 July 2025
- Published by MDPI AG in Preprints.org
scikit-activeml: A Comprehensive and User-friendly Active Learning Library
Scikit-activeml is a user-friendly open-source Python library for active learning on top of scikit-learn. Included are implementations of a large collection of query strategies, models, and visualization tools in pool- and stream-based active learning for classification or regression tasks with single or multiple annotators. The flexible design of the active learning cycle enables individual adaptations to a variety of learning scenarios. Our source code with comprehensive documentation is available at https://scikit-activeml.github.io.
- 4 July 2025
- Published by MDPI AG in Preprints.org
Open Accessscikit-activeml: A Comprehensive and User-friendly Active Learning Library
Scikit-activeml is a user-friendly open-source Python library for active learning on top of scikit-learn. Included are implementations of a large collection of query strategies, models, and visualization tools in pool- and stream-based active learning for classification or regression tasks with single or multiple annotators. The flexible design of the active learning cycle enables individual adaptations to a variety of learning scenarios. Our source code with comprehensive documentation is available at https://scikit-activeml.github.io.
- Top Cited PapersOpen Access
- 23 February 2025
- Published by Elsevier in Ecological Informatics
- Vol. 87
AudioProtoPNet: An interpretable deep learning model for bird sound classification
- 23 February 2025
- Published by Elsevier in Ecological Informatics
- Vol. 87
Top Cited PapersOpen AccessAudioProtoPNet: An interpretable deep learning model for bird sound classification
- 22 August 2024
- Published by Springer Nature
- p. 280-296
Fast Fishing: Approximating Bait for Efficient and Scalable Deep Active Image Classification
- 22 August 2024
- Published by Springer Nature
- p. 280-296
Fast Fishing: Approximating Bait for Efficient and Scalable Deep Active Image Classification
- Open Access
Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
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. ActiveBird2Vec 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.
Open AccessActive Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
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. ActiveBird2Vec 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.
- 17 September 2023
- Published by Springer Nature
- p. 55-74
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
- 17 September 2023
- Published by Springer Nature
- p. 55-74
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
- Open Access
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
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 currently no standardized evaluation protocol for transformer-based language models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for practitioners. To tackle this challenge, we propose the ActiveGLAE benchmark, 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.
Open AccessActiveGLAE: A Benchmark for Deep Active Learning with Transformers
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 currently no standardized evaluation protocol for transformer-based language models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for practitioners. To tackle this challenge, we propose the ActiveGLAE benchmark, 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.
- Open Access
Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods
The present work focuses on the prediction of the hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. The data considered focus on a novel hot forming process at different tool temperatures ranging from C to C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of C to C and at strain rates ranging from 0.001 s to 0.1 s 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 Zerilli–Armstrong model (Z–A) as reference. Related work focuses on predicting single data points of the curves that the model was trained on. Due to the way data were split with respect to training and testing data, it is possible to predict entire stress–strain curves. The model allows to decrease the number of required laboratory experiments, eventually 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 superior results, i.e., the highest error reduction of 91% with respect to the Mean Squared Error.Open AccessPredicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods
The present work focuses on the prediction of the hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. The data considered focus on a novel hot forming process at different tool temperatures ranging from C to C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of C to C and at strain rates ranging from 0.001 s to 0.1 s 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 Zerilli–Armstrong model (Z–A) as reference. Related work focuses on predicting single data points of the curves that the model was trained on. Due to the way data were split with respect to training and testing data, it is possible to predict entire stress–strain curves. The model allows to decrease the number of required laboratory experiments, eventually 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 superior results, i.e., the highest error reduction of 91% with respect to the Mean Squared Error.