M. Sc. Jan Schneegans

2022 [ to top ]

1.
Schneegans, J., Bieshaar, M., Sick, B.: A Practical Evaluation of Active Learning Approaches for Object Detection. Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. bll. 49–67 (2022).
[ Abstract ] [ BibTeX ] [ EndNote ] [ URL ]
 
Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.
@inproceedings{schneegans2022practical, abstract = {Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.}, author = {Schneegans, Jan and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {imported isac-www itegpub}, pages = {49–67}, title = {A Practical Evaluation of Active Learning Approaches for Object Detection}, year = 2022 }
%0 Conference Paper %1 schneegans2022practical %A Schneegans, Jan %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2022 %P 49--67 %T A Practical Evaluation of Active Learning Approaches for Object Detection %U http://ceur-ws.org/Vol-3259/ialatecml_paper5.pdf %X Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.

2021 [ to top ]

1.
Schneegans, J., Eilbrecht, J., Zernetsch, S., Bieshaar, M., Doll, K., Stursberg, O., Sick, B.: Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning -- A Case Study: Overtaking Cyclists. Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV (2021).
[ Abstract ] [ BibTeX ] [ EndNote ]
 
This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
@inproceedings{schneegans2021probabilistic, abstract = {This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.}, author = {Schneegans, Jan and Eilbrecht, Jan and Zernetsch, Stefan and Bieshaar, Maarten and Doll, Konrad and Stursberg, Olaf and Sick, Bernhard}, booktitle = {Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV}, keywords = {imported itegpub}, note = {(accepted)}, title = {Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning – A Case Study: Overtaking Cyclists}, year = 2021 }
%0 Conference Paper %1 schneegans2021probabilistic %A Schneegans, Jan %A Eilbrecht, Jan %A Zernetsch, Stefan %A Bieshaar, Maarten %A Doll, Konrad %A Stursberg, Olaf %A Sick, Bernhard %B Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV %D 2021 %T Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning -- A Case Study: Overtaking Cyclists %X This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
2.
Schneegans, J., Bieshaar, M., Heidecker, F., Sick, B.: Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks. Workshop on Integrated Artificial Intelligence in Data Science, ICPR. bll. 375–389. IEEE, Milan, Italy (2021).
[ BibTeX ] [ EndNote ]
 
@inproceedings{schneegans2021intelligent, address = {Milan, Italy}, author = {Schneegans, Jan and Bieshaar, Maarten and Heidecker, Florian and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {imported itegpub}, pages = {375–389}, publisher = {IEEE}, title = {Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks}, year = 2021 }
%0 Conference Paper %1 schneegans2021intelligent %A Schneegans, Jan %A Bieshaar, Maarten %A Heidecker, Florian %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 375--389 %R 10.1007/978-3-030-68799-1_27 %T Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks

2019 [ to top ]

1.
Schneegans, J., Bieshaar, M.: Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks. In: Tomforde, S. en Sick, B. (reds.) Organic Computing -- Doctoral Dissertation Colloquium 2018. bll. 45–60. kassel university press, Kassel, Germany (2019).
[ BibTeX ] [ EndNote ]
 
@incollection{schneegans2019smart, address = {Kassel, Germany}, author = {Schneegans, Jan and Bieshaar, Maarten}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2018}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {45–60}, publisher = {kassel university press}, title = {Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks}, year = 2019 }
%0 Book Section %1 schneegans2019smart %A Schneegans, Jan %A Bieshaar, Maarten %B Organic Computing -- Doctoral Dissertation Colloquium 2018 %C Kassel, Germany %D 2019 %E Tomforde, S. %E Sick, B. %I kassel university press %P 45--60 %T Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks

2018 [ to top ]

1.
Bieshaar, M., Depping, M., Schneegans, J., Sick, B.: Starting Movement Detection of Cyclists Using Smart Devices. IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE, Turin, Italy (2018).
[ BibTeX ] [ EndNote ]
 
@inproceedings{bieshaar2018starting, address = {Turin, Italy}, author = {Bieshaar, M. and Depping, M. and Schneegans, J. and Sick, B.}, booktitle = {IEEE International Conference on Data Science and Advanced Analytics (DSAA)}, keywords = {imported}, publisher = {IEEE}, title = {Starting Movement Detection of Cyclists Using Smart Devices}, year = 2018 }
%0 Conference Paper %1 bieshaar2018starting %A Bieshaar, M. %A Depping, M. %A Schneegans, J. %A Sick, B. %B IEEE International Conference on Data Science and Advanced Analytics (DSAA) %C Turin, Italy %D 2018 %I IEEE %R 10.1109/dsaa.2018.00042 %T Starting Movement Detection of Cyclists Using Smart Devices