ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Kim-Celine Kahl, Carsten T. Lueth, Maximilian Zenk, Klaus Maier-Hein, Paul F. Jaeger / ICLR 2024 Oral
Learn more Download
Recent successes in AI research may give the impression that society will soon benefit from
autonomous systems replacing human labor.
Behind the scenes, however, tedious manual tasks will remain an integral requirement of machine
learning systems for the foreseeable future,
be it in the form of monitoring outputs for failures, explaining autonomous decisions, or
labeling vast amounts of training data.
The field of Interactive Machine Learning tackles these challenges by setting aside the paradigm
of fully autonomous systems and instead placing the human at the center of AI application:
Only the design of human and machine as a symbiotic system from the ground up allows to harness
manual labor in the most efficient way and thus its reduction to a bare minimum.
Following this human-centered AI perspective, we focus on 3 impact areas:
To alleviate the burden of manually labeling vast amounts of training data, we enable human-in-the-loop training by transforming state-of-the-art machine learning models into interactive tools.
Comprehending a model’s predictions lies at the heart of human-machine interaction. We aim to extract the causal reasoning behind decisions and render insights accessible to domain experts.
One aspect of symbiotic decision making strives to alleviate the burden of monitoring predictions from imperfect models. To this end, we research the ability of systems to detect and flag their own failures.
Kim-Celine Kahl, Carsten T. Lueth, Maximilian Zenk, Klaus Maier-Hein, Paul F. Jaeger / ICLR 2024 Oral
Learn more DownloadCarsten T. Lueth, Till J. Bungert, Lukas Klein, Paul F. Jaeger / NeurIPS 2023
Learn more DownloadLukas Klein, Sebastian Ziegler, Felix Laufer, Charlotte Debus, Markus Goetz, Klaus Maier-Hein, Ulrich W. Paetzold, Fabian Isense and Paul F. Jaeger / Advanced Materials and NeurIPS 2023 XAIA Workshop Oral
Learn more DownloadPaul F. Jaeger, Carsten T. Lueth, Lukas Klein and Till J. Bungert / ICLR 2023 Oral
Learn more DownloadHelmholtz Imaging (HI) brings scientists and engineers in the Helmholtz Association together to promote and develop imaging science and to foster synergies across imaging modalities and applications within the Helmholtz Association.
Learn moreDKFZ is the largest biomedical research institute in Germany and a member of the Helmholtz Association of National Research Centers. In over 90 divisions and research groups, our more than 3,000 employees, of which more than 1,200 are scientists, are investigating the mechanisms of cancer, are identifying cancer risk factors and are trying to find strategies to prevent people from getting cancer.
Learn more