Research Associate (f/m/d)
Deep Learning Segmentation in Biomedical Imaging: An Unsupervised and Self-Supervised Approach
Organisationseinheit
Laboratorium für Applikationen der Synchrotronstrahlung (LAS)
Ihre Aufgaben
We are seeking a highly motivated person (f/m/d) to join our applied deep learning team and contribute to the development of state-of-the-art segmentation methods.
The successful candidate (f/m/d) will have the opportunity to work on cutting-edge research in the field of Deep learning (DL) applied to X-ray Computed Tomography (CT) data.
The goal of the project is to extend existing software and supervised semantic segmentation with unsupervised and weakly supervised techniques. Semantic image segmentation is a labor-intensive and time-consuming task that requires manual annotation by experts. Unsupervised learning involves learning patterns and features in data without explicit supervision or labeled data. Self-supervised learning (SSL) involves training a model to predict certain properties of the data. In the context of semantic image segmentation, SSL techniques can be used to train a model to predict different types of transformations, such as rotation, colorization, or jigsaw puzzles. The model can then use this knowledge to segment the images, without requiring pixel-level annotations. By leveraging these techniques, the efficiency of semantic image segmentation can be significantly improved, enabling faster and more cost-effective analysis of large-scale image datasets.
Your tasks within the project:
- Review state-of-the-art approaches for unsupervised, weakly supervised and self-supervised learning
- Implement the selected approaches
- Integrate the devised models into the segmentation software and workflows
Eintrittstermin
as soon as possible
Ihre Qualifikation
We are looking for a candidate with a strong scientific background and a passion for using AI technology to advance the biomedical field. If you have a PhD or Master's degree in Computer Science, Computer Vision, Machine Learning, or a related field; have a strong understanding of deep learning principles; interested to contribute to various applied projects in the field of biomedical imaging - we would like to hear from you.
They shall have:
- Master in computer science, mathematics or engineering
- In-depth understanding of the Deep Learning principles
- Good programming skills: Python, Git, OOP, and DL framework of choice are a must
- Experience with image processing and computer vision
- Track record of DL related publications is a plus
- Confidence in English
Salary
Salary category EG 13, depending on the fulfillment of professional and personal requirements.
Contract duration
limited for 3 years
Application up to
June 4, 2023
Contact person in line-management
For further information, please contact Dr. Alexey Ershov, email: alexey.ershov2@kit.edu.
Bitte bewerben Sie sich online über den unten stehenden Button für die Ausschreibungsnummer 2123/2023.
Ausschreibungsnummer: 2123/2023
Wir streben eine möglichst gleichmäßige Besetzung der Arbeitsplätze mit Beschäftigten (w/m/d) an und würden uns daher insbesondere über Bewerbungen von Frauen freuen.
Bei gleicher Eignung werden anerkannt schwerbehinderte Menschen bevorzugt berücksichtigt.
Kontakt
Bei allgemeinen Fragen zur Bewerbung:
Personalservice (PSE) - Personalbetreuung
Frau Carrasco Sanchez
Telefon: +49 721 608-42016,
Kaiserstr. 12, 76131 Karlsruhe