Do you want to create technology for the next generation of industry and society? Univrses is now looking for a Master Thesis student to join the team in Stockholm!

Univrses is a 3D Computer Vision and Machine Learning company based in Stockholm, creating high-end technologies for autonomous systems. We work in several different areas, but our main focus is on self-driving vehicles, mobile robotics and smart city development. Our team consists of hard-working and friendly people from all over the world with diverse backgrounds and expert knowledge in computer vision, robotics, machine learning, physics, math, software development and more.

Master Thesis at Univrses

Right now, we offer Master students the opportunity to be an integral part of the team while working on their Thesis. You will be working in a fun, stimulating and highly professional work environment together with our awesome team. This is truly a unique chance to work with some of the best scientists and engineers in Computer Vision and Robotics in the world.

Background

Semi-supervised learning is a machine learning paradigm that leverages both labelled and unlabeled data to improve model performance. In many real-world scenarios, however, datasets are characterized by extreme class imbalance, with very few labelled examples for certain classes. This imbalance presents a significant challenge for traditional semi-supervised learning methods, as they tend to focus on the majority class, neglecting the underrepresented classes. This thesis aims to explore novel techniques and strategies for improving semi-supervised learning performance in the presence of extreme class imbalance.

Goals

The primary objectives of this research are as follows:

1. Method Development: Develop and evaluate novel semi-supervised learning techniques specifically designed to handle datasets with extreme class imbalance. These methods should effectively leverage the small amount of labelled data available for minority classes while making use of abundant unlabeled data.
2. Performance Improvement: Evaluate the extent to which the model trained with the novel semi-supervised learning technique outperforms models trained only on labelled data.
3. Real-world Applications: Apply the proposed methods to real-world products, where class imbalance is a common challenge. Assess the practical utility and effectiveness of the developed techniques in these domains.

Relevant material

• Class-Imbalanced Semi-Supervised Learning
• Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
• A Survey on Semi-Supervised Semantic Segmentation
  

Required Background

Applicants are expected to possess a comprehensive understanding of deep learning and computer vision, which will be essential for engaging with the research effectively.

Proficiency in Python coding is a prerequisite for implementing and experimenting with the proposed techniques.

Required application material

• CV
• Cover letter
• Transcripts (with grades)

All application material must be in English.

Work starts in beginning of January 2024

Next step

Interested in joining Univrses as our new Master Thesis student? Submit your application - All application material must be in English!