II-2311 EXPLAINABLE IMAGE QUALITY ASSESSMENT OF SCIENTIFIC LOW-LIGHT IMAGES INTERNSHIP
Are you passionate about research? So are we! Come and join us
The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies.
You ‘d like to contribute as an intern? Join our IT for Innovation Services department
The IT for Innovative Services (ITIS) department, with its 100 researchers and engineers, focuses on the digital transformation of operations in organizations with traditional environments and digital ecosystems, with the aim of improving their performance and innovation capacity. The common thread throughout ITIS is to develop the most efficient use of big data to ensure the most appropriate decision-making processes.
The department relies on the Data Analytics Platform: a hybrid infrastructure covering the entire range of data analytics activities. The platform is based on three pillars: a high-performance computing (HPC) infrastructure, a cognitive analytics pillar and an interactive visualization wall (Viswall).
eXplainable ArtificiaI Intelligence (XAI) consists of developing AI models whose predictions and decisions can be interpreted by a human. This contrasts with the "black box" concept where even its designers cannot explain why an AI model leads to a specific result.
As a follow-up of a project, we plan to apply XAI in the field of Space Observation. This topic continues to fascinate medias and public, as shown by the extraordinary excitement after the frequent publications of images captured with the James Webb Telescope. By using recent automated telescopes (e.g. VAONIS), Electronically Assisted Astronomy allows everyone to capture images of celestial objects from any location (galaxies, nebula, stars clusters, planets and even comets).
In this context, the internship consists in designing and developing XAI models for Image Quality Assessment of scientific low-light images – to automatically evaluate the quality of images while allowing for the results interpretation.
How will you contribute?
You will be mainly in charge of:
- Review the state of the art about XAI and Image Quality Assessment for low-light images, then possibly propose original approaches and/or improvements.
- Design and implement the methods and improvements in a Python prototype.
- Test the prototype on existing high-resolution data (example: MILAN Sky Survey -- https://publicationid.list.lu/milan-sky-survey-raw-images-captured-with-a-stellina-observation-station)
- Document the code and write a report describing the technical/scientific contribution, the evaluation results. If applicable, the results will lead to an academic publication.
Is Your profile described below? Are you our future colleague? Apply now!
- You are currently completing a Master 1 or 2 in Computer Science or in an AI-oriented field
Experience and skills
- Proactive and independent skill set with the ability to take initiative
- Good understanding of Machine Learning/Deep Learning
- Knowledge of Python, Tensorflow/Pytorch or equivalent
- Nice to have: experience with Image processing
- Fluent in English and French
Your LIST benefits
An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects;
Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society;
Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations such as our Viswall, high-scale incubators and top of the range 3D/4D printings that are part of our toolkit for excelling in all we do;
Multicultural and international work environment with more than 45 nationalities represented in our workforce;
Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions;
Gender-friendly environment with multiple actions to attract, develop and retain women in science;
32 days’ paid annual leave for a full time internship, 11 public holidays per annum, flexible working hours,
An environment encouraging curiosity, innovation and entrepreneurship in all areas.
Your application must include a motivation letter oriented towards the position and detailing your experience
Application procedure and conditions:
- LIST is an equal opportunity employer and is committed to hiring and retaining diverse personnel. We value all applicants and will consider all competent candidates for employment without regard to national origin, race, colour, gender, sexual orientation, gender identity, marital status, religion, age or disability;
- Applications will be reviewed on an ongoing basis until the position is filled;
- An assessment committee will review the applications and select candidates based on guidelines that aim to ensure equal opportunities;
- The main criteria for selection will be the correspondence of the existing skills and expertise of the applicant with the requirements mentioned above.
- Read C1 AdvancedWrite C1 AdvancedSpeak C1 Advanced
- Read C1 AdvancedWrite C1 AdvancedSpeak C1 Advanced