Prof. Dr.-Ing. Erhardt Barth

@misc{KrBa22,
author = {Hajo Nils Krabbenh{\"o}ft and Erhardt Barth},
title = {{TEVR}: {I}mproving {S}peech {R}ecognition by {T}oken {E}ntropy {V}ariance {R}eduction},
publisher = {arXiv},
year = {2022},
keywords = {Computation and Language (cs.CL), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, F.2.1; I.2.6; I.2.7},
doi = {10.48550/ARXIV.2206.12693},
url = {https://arxiv.org/abs/2206.12693},
copyright = {Creative Commons Attribution 4.0 International}
}

@article{ThKlMaGrKaBaKrMa22,
  title={Automated assessment of immunofixations with deep neural networks},
  author={Thiemann, Christian and Klitzke, Britta and Martinetz, Philipp and Gr{\"u}ning, Philipp and K{\"a}ster, Thomas and Barth, Erhardt and Kramer, Jan and Martinetz, Thomas},
  journal={Journal of Laboratory Medicine},
  volume={46},
  number={5},
  pages={331--336},
  year={2022},
  publisher={De Gruyter},
  url={https://www.degruyter.com/document/doi/10.1515/labmed-2022-0078/pdf}
}

@article{GrMaBa22,
  title={FP-nets as novel deep networks inspired by vision},
  author={Gr{\"u}ning, Philipp and Martinetz, Thomas and Barth, Erhardt},
  journal={Journal of Vision},
  volume={22},
  number={1},
  pages={8--8},
  year={2022},
  publisher={The Association for Research in Vision and Ophthalmology},
  url={https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrMaBa22.pdf}
}

@inproceedings{MaLaSiSiBiKaBaBaMa21,
  title = {An {AI}-based Framework for Diagnostic Quality Assessment of Ankle Radiographs},
  author = {Mairh{\"o}fer, Dominik and Laufer, Manuel and Simon, Paul Martin and Sieren, Malte and Bischof, Arpad and K{\"a}ster, Thomas and Barth, Erhardt and Barkhausen, J{\"o}rg and Martinetz, Thomas},
  booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning},
  pages = {484--496},
  year = {2021},
  editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris},
  volume = {143},
  series = {Proceedings of Machine Learning Research},
  month = {07--09 Jul},
  publisher = {PMLR},
  pdf = {https://proceedings.mlr.press/v143/mairhofer21a/mairhofer21a.pdf},
  url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/MaLaSiSiBiKaBaBaMa21.pdf},
  abstract = {The quality of radiographs is of major importance for diagnosis and treatment planning. While most research regarding automated radiograph quality assessment uses technical features such as noise or contrast, we propose to use anatomical structures as more appropriate features. We show that based on such anatomical features, a modular deep-learning framework can serve as a quality control mechanism for the diagnostic quality of ankle radiographs. For evaluation, a dataset consisting of 950 ankle radiographs was collected and their quality was labeled by radiologists. We obtain an average accuracy of 94.1%, which is better than the expert radiologists are on average.}
}

@article{AlLiAbBaMa21,
author={Hammam Alshazly and Christoph Linse and Mohamed Abdalla and Erhardt Barth and Thomas Martinetz},
title = {{COVID-Nets}: deep {CNN} architectures for detecting {COVID-19} using chest {CT} scans},
journal = {PeerJ Computer Science},
volume={7},
pages={e655},
year={2021},
doi = {10.7717/peerj-cs.655},
url = {https://doi.org/10.7717/peerj-cs.655}
}

@article{GrBa21a,
  title={{FP}-{N}ets for {B}lind {I}mage {Q}uality {A}ssessment},
  author={Gr{\"u}ning, Philipp and Barth, Erhardt},
  journal={Journal of Perceptual Imaging},
  volume={4},
  number={1},
  pages={10402-1--10402-13},
  year={2021},
  url={https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrBa21a.pdf}
}

@article{AlLiBaIdMa21,
author = {Hammam Alshazly and Christoph Linse and Erhardt Barth and Sahar Ahmed Idris and Thomas Martinetz},
journal = {IEEE Access},
title = {{T}owards {E}xplainable {E}ar {R}ecognition {S}ystems {U}sing {D}eep {R}esidual {N}etworks},
year = {2021},
pages = {1-1},
doi = {10.1109/ACCESS.2021.3109441},
url = {https://doi.org/10.1109/ACCESS.2021.3109441}
}

@inproceedings{GrBa21,
  title={Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks},
  author={Gr{\"u}ning, Philipp and Barth, Erhardt},
  booktitle={SVRHM 2021 Workshop NeurIPS},
  year={2021},
  url={https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrBa21.pdf}
}

@inproceedings{GrNeHeSoBa21,
  title={Direct Inference of Cell Positions using Lens-Free Microscopy and Deep Learning},
  author={Gr{\"u}ning, Philipp and Nette, Falk and Heldt, Noah and de Souza, Ana Cristina Guerra and Barth, Erhardt},
  booktitle={Medical Imaging with Deep Learning},
  pages={219--227},
  year={2021},
  organization={PMLR},
  url={https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrNeHeSoBa21.pdf}
}

@article{AlLiBaMa21,
author={Hammam Alshazly and Christoph Linse and Erhardt Barth and Thomas Martinetz},
title = {Explainable {COVID-19} {D}etection {U}sing {C}hest {CT} {S}cans and {D}eep {L}earning},
journal = {Sensors},
volume={21},
number={2},
pages={455},
year={2021},
publisher={Multidisciplinary Digital Publishing Institute},
url = {https://www.mdpi.com/1424-8220/21/2/455},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/AlLiBaMa21.pdf}
}

@inproceedings{GrMaBa20a,
author={Gr{\"u}ning, Philipp and Martinetz, Thomas and Barth, Erhardt},
editor={Farka{\v{s}}, Igor and Masulli, Paolo and Wermter, Stefan},
title={Log-Nets: Logarithmic Feature-Product Layers Yield More Compact Networks},
booktitle={Artificial Neural Networks and Machine Learning -- ICANN 2020},
year={2020},
publisher={Springer International Publishing},
address={Cham},
pages={79--91},
abstract={We introduce Logarithm-Networks (Log-Nets), a novel bio-inspired type of network architecture based on logarithms of feature maps followed by convolutions. Log-Nets are capable of surpassing the performance of traditional convolutional neural networks (CNNs) while using fewer parameters. Performance is evaluated on the Cifar-10 and ImageNet benchmarks.},
isbn={978-3-030-61616-8}
}

@article{AlLiBaMa20,
  title={Deep {C}onvolutional {N}eural {N}etworks for {U}nconstrained {E}ar {R}ecognition},
  author={Hammam Alshazly and Christoph Linse and Erhardt Barth and Thomas Martinetz},
  journal={IEEE Access},
  publisher={IEEE},
  volume={8},
  pages={170295--170310},
  year={2020},
  url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/AlLiBaMa20.pdf}
}

@article{GrPaZiBaMa20,
title={A task-dependent active learning method for axon segmentation with CNNs},
author={Gr{\"u}ning, Philipp and Palumbo, Alex and Zille, Marietta and Barth, Erhardt and Mamlouk, Amir Madany},
journal={Proceedings on Automation in Medical Engineering},
volume={1},
number={1},
pages={025--025},
year={2020},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrPaZiBaMa20.pdf}
}

@article{GrMaBa20,
  title={Feature Products Yield Efficient Networks},
  author={Gr{\"u}ning, Philipp and Martinetz, Thomas and Barth, Erhardt},
  journal={arXiv preprint arXiv:2008.07930},
  year={2020},
  url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/GrMaBa20.pdf}
}

@article{AlLiBaMa19a,
  title={{Handcrafted versus CNN Features for Ear Recognition}},
  author={Hammam Alshazly and Christoph Linse and Erhardt Barth and Thomas Martinetz},
  journal={Symmetry},
  volume={11},
  number={12},
  pages={1493},
  year={2019},
  url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/AlLiBaMa19a.pdf}
}

@article{Kumar-etal19,
  title={A multi-organ nucleus segmentation challenge},
  author={Kumar, Neeraj and Verma, Ruchika and Anand, Deepak and Zhou, Yanning and Fahri Onder, Omer and Tsougenis, Efstratios and Chen, Hao and Heng, Pheng-Ann and Li, Jiahui and Hu, Zhiqiang and Wang, Yunzhi and Alemi Koohbanani, Navid and Jahanifar, Mostafa and Zamani Tajeddin, Neda and Gooya, Ali and Rajpoot, Nasir and Ren, Xuhua and Zhou, Sihang and Wang, Qian and Shen, Dinggang and Yang, Cheng-Kun and Weng, Chi-Hung and Yu, Wei-Hsiang and Yeh, Chao-Yuan and Yang, Shuang and Xu, Shuoyu and Hei Yeung, Pak and Sun, Peng and Mahbod, Amirreza and Schaefer, Gerald and Ellinger, Isabella and Ecker, Rupert and Smedby, Orjan and Wang, Chunliang and Chidester, Benjamin and Ton, That-Vinh and Tran, Minh-Triet and Ma, Jian and N Do, Minh and Graham, Simon and Dang Vu, Quoc and Tae Kwak, Jin and Gunda, Akshaykumar and Chunduri, Raviteja and Hu, Corey and Zhou, Xiaoyang and Lotfi, Dariush and Safdari, Reza and Kascenas, Antanas and O’Neil, Alison and Eschweiler, Dennis and Stegmaier, Johannes and Cui, Yanping and Yin, Baocai and Chen, Kailin and Tian, Xinmei and Gr{\"u}ning, Philipp and Barth, Erhardt and Arbel, Elad and Remer, Itay and Ben-Dor, Amir and Sirazitdinova, Ekaterina and Kohl, Matthias and Braunewell, Stefan and Li, Yuexiang and Xie, Xinpeng and Shen, Linlin and Ma, Jun and Das Baksi, Krishanu and Azam Khan, Mohammad and Choo, Jaegul and Colomer, Adrián and Naranjo, Valery and Pei, Linmin and M Iftekharuddin, Khan and Roy, Kaushiki and Bhattacharjee, Debotosh and Pedraza, Anibal and Gloria Bueno, Maria and Devanathan, Sabarinathan and Radhakrishnan, Saravanan and Koduganty, Praveen and Wu, Zihan and Cai, Guanyu and Liu, Xiaojie and Wang, Yuqin and Sethi, Amit},
  journal={IEEE transactions on medical imaging},
  volume={39},
  number={5},
  pages={1380--1391},
  year={2019},
  publisher={IEEE}
}

@article{AlLiBaMa19,
author={Hammam Alshazly and Christoph Linse and Erhardt Barth and Thomas Martinetz},
title = {Ensembles of {D}eep {L}earning {M}odels and {T}ransfer {L}earning for {E}ar {R}ecognition},
journal = {sensors},
volume={19},
number={19},
pages={4139},
year={2019},
publisher={Multidisciplinary Digital Publishing Institute},
url = {https://www.mdpi.com/1424-8220/19/19/4139},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/AlLiBaMa19.pdf}
}

@misc{NiFoKnBa,
author = {J. Niemeijer and P. Pekezou Fouopi and S. Knake-Langhorst and E. Barth},
title = {A {R}eview of {N}eural {N}etwork based {S}emantic {S}egmentation for {S}cene {U}nderstanding in {C}ontext of the self driving {C}ar},
comment = {Student Conference on Medical Engineering Science},
year = {2017}
}

@inproceedings{SeSeBa17,
author = {Stanislau Semeniuta and Aliaksei Severyn and Erhardt Barth},
title = {A Hybrid Convolutional Variational Autoencoder for Text Generation},
booktitle = {{EMNLP}},
pages = {627--637},
publisher = {Association for Computational Linguistics},
year = {2017}
}

@inproceedings{KnBaMa17,
author = {Boris Knyazew and Erhardt Barth and Thomas Martinetz},
title = {Recursive autoconvolution for unsupervised learning of convolutional neural networks}, 
journal = {2017 International Joint Conference on Neural Networks (IJCNN)},
pages = {2486--2493},
year = {2017}
}

@inproceedings{BuMaBa17,
author= {Irina Burciu and Thomas Martinetz and Erhardt Barth},
editor= {Jacques Blanc-Talon and Rudi Penne and Wilfried Philips and Dan Popescu and Paul Scheunders},
title = {Sensing {F}orest for {P}attern {R}ecognition},
booktitle = {Advanced Concepts for Intelligent Vision Systems: 18th International Conference, {ACIVS} 2017},
series = {Lecture Notes in Computer Science},
volume = {10617},
year = {2017},
publisher = {Springer},
pages = {126--137},
url = {https://link.springer.com/chapter/10.1007/978-3-319-70353-4_11}
}

@article{BrBaRe17,
author = {A. Brachmann and e. Barth and C. RedieS},
title = {Using {CNN} features to better understand what makes visual artworks special},
journal = {Frontiers in Psychologie 8},
pages = {830},
year = {2017}
}

@article{ScBaMa16,
author = {Sch{\"u}tze, Henry and Barth, Erhardt and Martinetz, Thomas},
title = {{L}earning {E}fficient {D}ata {R}epresentations with {O}rthogonal {S}parse {C}oding},
journal = {IEEE Transactions on Computational Imaging},
volume = {2},
number = {3},
month = {09},
pages = {177--189},
ISSN = {2333-9403},
year = {2016},
doi = {10.1109/TCI.2016.2557065},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/ScBaMa16.pdf}
}

@inproceedings{SeBa16,
author = {Stanislau Semeniuta and  Erhardt Barth},
title = {Image classification with recurrent attention models},
booktitle = {{SSCI}},
pages = {1--7},
publisher = {{IEEE}},
year = {2016}
}

@inproceedings{SeSeBa16,
author = {Stanislau Semeniuta and Aliaksei Severyn and Erhardt Barth},
title = {Recurrent Dropout without Memory Loss},
booktitle = {{COLING}},
pages = {1757--1766},
publisher = {{ACL}},
year = {2016}
}