Internship | Selective feedback for adjusting object detection models for domain shifts
About this position
Advancements in deep learning and computer vision have made it possible to accurately detect and classify objects given enough (relevant) training data. However, models for object detection are still far from perfect when they are deployed in real-life applications. Specific objects might not be detected (false negatives) or objects might be falsely detected where there are no objects (false positives). A common reason for this drop in performance is that the training dataset is different from the data at deployment time (e.g. different backgrounds, camera viewpoints, lighting conditions, object appearance). In this project, we will explore how to improve a model by selective feedback, ideally with as few manual interventions as possible.
What will be your role?
In this project, you will research methods for determining which of the resulting detections should be annotated in order to improve the performance of the model (active learning). This involves the challenges of (a) Finding the detections that are actually objects and that would enrich the model because they are complementary to the train set. This is to improve recall, e.g., by searching for low-confidence positives. (b) Finding the false positives (background) and feeding them back as negatives. This is to improve precision, e.g., suppressing hard negatives. We envision the simulation of deployment by going from one domain (train) to a second, different domain (deployment). In the second domain, we have a subset for adjustment of the model by more labels (as few as possible) on initial detections, and another subset for testing the models respectively without and with adjustment (to measure the performance gain).
What we expect from you
You are in the final stages of your master’s degree in artificial intelligence, computer science, physics, mathematics, electrical engineering, systems and control engineering, or a similar degree and have a track record in the field of computer vision or deep learning. Experience in programming (Python) and deep learning is necessary (e.g. PyTorch of TensorFlow). Preferably, you are available fulltime for a period between 6 to 12 months. Please mention in your application whether you are looking for an internship or graduation project and the desired duration of the project/internship you are looking for.
What you'll get in return
You want to work on the precursor of your career; a work placement 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. Naturally, we provide suitable work placement compensation.
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. Read more about TNO as an employer.
At TNO we encourage an inclusive work environment, where you can be yourself. Whatever your story and whatever unique qualities you bring to the table. It is by combining our unique strengths and perspectives that we are able to develop innovations that make a real difference in society. Want to know more? Read what steps we are taking in the area of diversity and inclusion.
The selection process
After the first CV selection, the application process will be conducted by the concerning department. TNO will provide a suitable internship agreement. If you have any questions about this vacancy, you can contact the contact person mentioned below.
For this internship vacancy it is required that the AIVD issues a security clearance (VGB) after conducting a security screening. Take into account that this process may take about 8 weeks. If you have been abroad for more than 6 consecutive months, or if you do not have the Dutch nationality, it may take longer. Read more about security screening on the AIVD website.
Has this job opening sparked your interest?
Then we’d like to hear from you! Please contact us for more information about the job or the selection process. To apply, please upload your CV and covering letter using the ‘apply now’ button.
More information about this vacancy?
Anne-Maartje den Uijl-MeijmanFunctie:Recruiter