Methods Beyond Supervised Learning

Our group’s research focuses on machine learning problems that move beyond needing large amounts of human annotation. Current projects include:

• unsupervised deep learning

• positive unlabeled learning

• deep metric learning

• semi-supervised learning

• self-supervised learning methods for vision, bioinformatics, and multimodal dataset

Members

Publications

1. Weber T, Ingrisch M, Bischl B, Rügamer D (2023) Unreading Race: Purging Protected Features from Chest X-ray Embeddings. arXiv:2311.01349.
   link|pdf.
2. Ott F, Rügamer D, Heublein L, Bischl B, Mutschler C (2023) Auxiliary Cross-Modal Representation Learning With Triplet Loss Functions for Online Handwriting Recognition. IEEE Access 11, 94148–94172.
3. Weber T, Ingrisch M, Bischl B, Rügamer D (2023) Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis Advances in Knowledge Discovery and Data Mining: 27th Pacific-Asia Conference, PAKDD 2023,
   link|pdf.
4. Ott F, Raichur NL, Rügamer D, Feigl T, Neumann H, Bischl B, Mutschler C (2023) Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression. arXiv:2208.00919.
   link|pdf.
5. Scholbeck CA, Funk H, Casalicchio G (2023) Algorithm-Agnostic Feature Attributions for Clustering. In: In: Longo L (ed) Explainable Artificial Intelligence, pp. 217–240. Springer Nature Switzerland, Cham.
   link | pdf.
6. Ott F, Rügamer D, Heublein L, Bischl B, Mutschler C (2022) Representation Learning for Tablet and Paper Domain Adaptation in favor of Online Handwriting Recognition MPRSS 2022,
7. Rezaei M, Dorigatti E, Rügamer D, Bischl B (2022) Joint Debiased Representation Learning and Imbalanced Data Clustering arXiv preprint arXiv:2109.05232,
   link|pdf.
8. Ott F, Rügamer D, Heublein L, Hamann T, Barth J, Bischl B, Mutschler C (2022) Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens. International Journal on Document Analysis and Recognition (IJDAR).
   link|pdf.
9. Ott F, Rügamer D, Heublein L, Bischl B, Mutschler C (2022) Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift ACM Multimedia,
   link|pdf.
10. Klaß A, Lorenz S, Lauer-Schmaltz M, Rügamer D, Bischl B, Mutschler C, Ott F (2022) Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift IJCAI-ECAI 2022, 1st International Workshop on Spatio-Temporal Reasoning and Learning,
11. Ott F, Rügamer D, Heublein L, Bischl B, Mutschler C (2022) Cross-Modal Common Representation Learning with Triplet Loss Functions. arXiv preprint arXiv:2202.07901.
    link|pdf.
12. Dorigatti E, Goschenhofer J, Schubert B, Rezaei M, Bischl B (2022) Positive-Unlabeled Learning with Uncertainty-aware Pseudo-label Selection. arXiv preprint arXiv:2109.05232.
    link|pdf.
13. Goschenhofer J, Hvingelby R, Rügamer D, Thomas J, Wagner M, Bischl B (2021) Deep Semi-Supervised Learning for Time Series Classification 20th IEEE International Conference on Machine Learning and Applications (ICMLA),
    link | pdf.
14. Rezaei M, Soleymani F, Bischl B, Azizi S (2021) Deep Bregman Divergence for Contrastive Learning of Visual Representations. arXiv preprint arXiv:2109.07455.
15. Soleymani F, Eslami M, Elze T, Bischl B, Rezaei M (2021) Deep Variational Clustering Framework for Self-labeling of Large-scale Medical Images. arXiv preprint arXiv:2109.10777.
16. Goschenhofer J, Ragupathy P, Heumann C, Bischl B, Aßenmacher M (2022) CC-Top: Constrained Clustering for Dynamic Topic Discovery Workshop on Ever Evolving NLP (EvoNLP), Association for Computational Linguistics, Abu Dhabi, United Arab Emirates.
    link|pdf.
17. Dexl J, Benz M, Kuritcyn P, Wittenberg T, Bruns V, Geppert C, Hartmann A, Bischl B, Goschenhofer J (2022) Robust Colon Tissue Cartography with Semi-Supervision. Current Directions in Biomedical Engineering 8, 344–347.
    link|pdf.