Master Thesis : Generating a realistic synthetic dataset for semantic segmentation using diffusion models
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
Semantic segmentation is a fundamental task in computer vision, playing a crucial role in various applications such as autonomous driving, medical image analysis, and object recognition. Deep learning models have shown remarkable performance in semantic segmentation, but their success largely depends on the availability of high-quality labeled datasets for training. The scarcity of diverse and comprehensive labeled datasets, especially in specific domains or for rare objects, hinders the development and evaluation of robust semantic segmentation models.
One promising solution to address the data scarcity problem is the generation of synthetic datasets. However, creating a synthetic dataset that accurately mimics real-world data remains a challenging task. Current synthetic datasets often suffer from unrealistic artifacts, which can lead to poor model generalization when trained on them.
Goals
The primary objectives of this research are as follows:
- Diffusion Model Adaptation: Investigate the adaptation and extension of diffusion models for generating high-quality synthetic datasets for semantic segmentation. This includes developing methods to ensure that generated images exhibit realistic object shapes, textures, and environmental contexts.
- Quality Assessment: Develop quantitative and qualitative metrics for assessing the quality of the synthetic dataset. Ensure that the dataset meets the necessary criteria for training and evaluating semantic segmentation models.
- Performance Improvement: Evaluate the extent to which semantic segmentation models trained on the synthetic dataset outperform models trained on existing synthetic datasets or when real data is scarce.
Relevant material
- Denoising Diffusion Probabilistic Models
- Effective Data Augmentation With Diffusion Models
- DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
- DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
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.
While prior experience with diffusion models is highly valued, it is not mandatory, as this thesis will provide the necessary context and guidance for their application in generating realistic synthetic datasets for semantic segmentation.
Required application material
- CV
- Cover letter
- Transcripts (with grades)
All application material must be in English.
Work starts in beginning of 2024
Next step
Interested in joining Univrses as our new Master Thesis student? Submit your application - All application material must be in English!
- Department
- Tech
- Role
- Master Thesis Student
- Locations
- Stockholm
- Remote status
- Temporarily Remote
Stockholm
Working at Univrses
-
World-leading technologies
You will work with unique solutions that will change the way industries operate and societies develop -
World-leading team
You will work in a diverse and friendly team with the world's most skilled scientists and expert engineers within the field -
Generous employee benefits
You will be offered a competitive salary, flexible work hours, pension plan and weekly Lunch&Learns, among other things -
Offices in the center of Stockholm
During non-pandemic times, you will work from our bright and spacious facilities in the heart of Södermalm, Stockholm
About Univrses
Univrses is a 3D Computer Vision and Machine Learning company, based in Sweden. We create high-end technologies for autonomous systems, and specialize in self-driving vehicles, mobile robotics and smart city development. The team consists of programmers and PhDs within fields such as computer vision, machine learning, robotics, software development, maths and physics.
Master Thesis : Generating a realistic synthetic dataset for semantic segmentation using diffusion models
Loading application form
Already working at Univrses?
Let’s recruit together and find your next colleague.