Master's thesis: Towards Interpretable Image Segmentation Using Part-Prototypes

Delve into a master’s thesis that sits at the intersection of innovation and utility. Your task: to bridge the gap between interpretable part-prototype models and advanced image segmentation. By researching and crafting an architecture that applies explainable mechanisms to segment images, you will contribute to a growing field with vast implications in technology and society. Your work could shape future applications in essential sectors such as healthcare, autonomous navigation, and security.   

Solliciteer direct

Required interest(s)

  • Computer Vision
  • Explainable AI/XAI
  • Object Detection
  • Image Segmentation

What do you get

  • A challenging assignment within a practical environment
  • € 1000 compensation, € 500 + lease car or € 600 + living space
  • Professional guidance
  • Courses aimed at your graduation period
  • Support from our academic Research center at your disposal
  • Two vacation days per month

What you will do

  • 65%  Research
  • 10%  Analyze, design, realize
  • 25%  Documentation

Image segmentation refers to the process of detecting and isolating specific objects or regions of interest within an image. It can help to accurately extract information that is relevant to an image, which can then be used for different purposes or even fed to other models—for example, human action recognition, object tracking, or background removal. When automated, image segmentation can become a powerful tool for several fields and applications, such as medical image processing, autonomous driving, agriculture, and video surveillance.

On the other hand, interpretable part-prototype models have been a recent subject of study in the field of computer vision. These models learn prototypical parts and recognize these components within images. They are able to infer a decision tree-like mechanism to determine their final prediction, where the tree steps correspond to different prototypes. Thus, part-prototype models are explainable by design, as they combine both prediction and explanation.

Image segmentation has typically been used in combination with prior image classification and object detection. Part-prototype models have been mainly used for image classification and, to a lesser extent, for object detection—but not yet for object segmentation, as far as public research indicates.

Assignment

The goal of this project would be to investigate the possibilities of interpretable part-prototype models and to develop a novel architecture that applies the part-prototype mechanism to image segmentation.

About Info Support Research Center

We anticipate on upcoming and future challenges and ensures our engineers develop cutting-edge solutions based on the latest scientific insights. Our research community proactively tackles emerging technologies. We do this in cooperation with renowned scientists, making sure that research teams are positioned and embedded throughout our organisation and our community, so that their insights are directly applied to our business. We truly believe in sharing knowledge, so we want to do this without any restrictions.

Read more about Info Support Research here.

What does Info Support offer you during your graduation period?

Of course, we offer you an excellent package of graduation conditions with various options. These include:

  • Laptop, all necessary tools, and development environments to successfully carry out your assignment
  • A graduation allowance, where you have the choice of:
    • € 1000 gross per month
    • € 500 gross per month + lease car with fuel card
    • € 600 gross per month + accommodation in Veenendaal

During your graduation internship, you will be included in one of our business units and in our Research Center. This will give you a good understanding of the developments within our projects and our research projects.

In addition, Info Support offers you:

  • A challenging master’s thesis at a solid, growing, and financially healthy company
  • Professional and experienced guidance, hybrid working
  • A graduation program with, among other things, training sessions, knowledge evenings, project visits, activities, and team, unit, and company outings
  • Experimentation with new products and releases that are in the pre-release phase
  • Brainstorming with other graduates and IT colleagues who are collegial and passionate
  • Potential for a permanent position in our IT Top Traineeship program!

About Info Support

Info Support specializes in custom software, data/AI solutions, management, and training and is active in the Finance, Industry, Agriculture, Food & Retail, Mobility & Public, and Healthcare sectors. We provide solid and innovative solutions for complex and critical software issues. Our headquarters are located in Veenendaal (NL) and Mechelen (BE). At present, approximately 500 employees are employed by Info Support.

Info Support’s working method is characterized by a number of core values: solidity, integrity, craftsmanship, and passion. These core values are intertwined in our work and the way we interact with each other. This year, we were also named a Top Employer in the Netherlands!

To ensure that all employees are always up to date with the latest developments, Info Support has an in-house knowledge center that eagerly satisfies the hunger for more or different knowledge and skills.

Procedures

  1. 1
  2. Kennismakingsgesprek

    Na je sollicitatie plannen we iets in en bespreken je (studie) loopbaan, interesses en ambities. We vertellen je over Info Support en jij kan al je vragen stellen.

  1. 2
  2. Assessment

    Gaan we verder? Dan doe je een assessment van je professionele kennis en persoonlijkheid (capaciteit, competenties en motieven).

  1. 3
  2. Selectie interview

    Vervolgens plannen we een selectie interview waarin we dieper ingaan op je professionele kennis en je persoonlijkheid.

  1. 4
  2. De ondertekening van een contract

    Verloopt alles positief dan ontvang je een contractaanbieding. Zijn we het eens? Dan starten we de pre-employment screening en nodigen we je uit voor de tekenmomenten.

Ontmoet Info Supporters