Internship | Beyond Classification: Open-Vocabulary Part Reasoning with VLMs

Internship | Beyond Classification: Open-Vocabulary Part Reasoning with VLMs

About this position

In many computer vision applications, especially in defense and security, it is not enough to classify an object, we often want to describe why it belongs to a certain class. For example, a vehicle might be classified as a “communication vehicle” because it has an antenna. This kind of reasoning relies on detecting attributes or parts that are not always exhaustively annotated, and where the presence of an attribute may be uncertain. Traditional classification pipelines are not well-suited for this, as they typically treat attributes as auxiliary to the main task.

What will be your role?

This project is part of ongoing research at TNO into explainable AI and vision-language models. You will start with a literature study on (training-free) attribute detection, sparse annotation, and part-based reasoning. Based on this, you will identify a suitable research gap and define a small-scale experimental setup using existing VLMs (e.g., CLIP) and open datasets. You will implement and evaluate a method for attribute detection in a setting with sparse or uncertain part annotations, and analyze how well it supports compositional reasoning. During your internship, you will write a thesis to document your research. If the results are promising, a joint publication may be considered.

You will perform this assignment within TNO’s Intelligent Imaging department. The Intelligent Imaging department is a passionate, creative, and dedicated team of professionals (60 people) specialized in developing groundbreaking applications in the field of computer vision. Our team members have diverse backgrounds, ranging from the medical field to artificial intelligence. Intelligent Imaging is a young and growing department which has built up a lot of expertise over the past years in AI and deep learning.

Recent work (e.g., Compositional Caching, CVPR 2025) shows that it is possible to detect attributes in a training-free and open-vocabulary way, using vision-language models (VLMs) and web-scale image caches. This opens up new possibilities for sparse, compositional, and explainable attribute detection, especially in domains where annotation is expensive or ambiguous.

We are interested in exploring how such attribute detection methods can be used to support independent reasoning about object class and object parts. In particular, we want to investigate how well these methods work in scenarios where annotations are sparse, uncertain, or compositional (e.g., “vehicle with antenna” vs. “vehicle with turret”).

What we expect from you

You are in the final stages of your master’s degree in artificial intelligence, computer science, data science, or a related field. You have experience with Python, deep learning, and preferably some familiarity with vision-language models. You are curious about how AI can be made more interpretable and robust in real-world settings.

We expect you to work from our office in The Hague (Oude Waalsdorperweg 63, Den Haag) at least two days per week, but preferably more often.

Your supervision team will consist of experienced researchers in computer vision and deep learning and are actively involved in related projects. They have experience with VLMs and have a strong track record in student supervision.

Please include the following practical information in your cover letter:

• Whether you are looking for an internship or a graduation project.
• The preferred duration of your project (flexible in the range of 6 to 12 months).
• Your desired start date (flexible, but due to the required security screening the earliest possible start date is three months after submitting your application).

What you'll get in return

You want an internship opportunity on the precursor of your career; an internship gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Furthermore, we provide:

• A highly professional, innovative internship environment, within a team of top experts.
• A suitable internship allowance (615 euro for wo-, hbo- and mbo-students, for a full-time internship).
• Possibility of eight hours of free leave per internship month (for a full-time internship).
• Use of a laptop.
• An allowance for travel expenses in case you don’t receive an OV-card.

TNO as an employer

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy. Since 1932, we have been making knowledge and technology available for the common good. We find each other in wonder and ingenuity. We are driven to push boundaries. There is all the space and support for your talent and ambition. You work with people who will challenge you: who inspire you and want to learn from you. Our state-of-the-art facilities are there to realize your vision. What you do at TNO matters: impact makes the difference. Because with every innovation you contribute to tomorrow’s world.

More information about this vacancy?

• Pieter Piscaer

  • E-mailadres: pieter.piscaer@tno.nl