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.