Master Thesis - Generative AI models for fashion - Under tillsättning eller tillsatt, ej sökbar

Project goal
Build a generative image-to-text AI model for used clothes, and furthermore use text prompts to modify the image.

Background and purpose
The fashion industry is shifting its focus from solely creating new clothing to promoting the reuse and recycling of existing garments. Our research encompasses two projects, one backed by Vinnova and the other by the EU, aimed at harnessing the power of AI for automating clothing reuse. Traditional human sorters typically undergo extensive training lasting several months to assess the best way to repurpose clothing items, and their decisions are often prone to errors. We are investigating how AI can enhance the sorting process by minimizing errors and expediting decision-making, ultimately optimizing the reuse of clothes.

About the project
The project will commence by delving into the realm of state-of-the-art generative AI methods, which may entail a comprehensive review of pertinent research papers and the implementation of cutting-edge techniques. While some publicly available large models like OpenFlamingov2 and ControlNet exhibit commendable zero-shot performance, they may not always fully meet specific project requirements. It's worth noting that fine-tuning these substantial models often demands substantial computing resources.

Our primary focus will be on leveraging a clothing dataset established through collaboration with Wargön Innovation AB. Working alongside researchers at RISE Linköping, the student will undertake the training of generative models using fashion data and conduct a comprehensive analysis of model performance based on various evaluation metrics. We provide GPU resources that the student can utilize for both training and evaluating models. However, it's important to mention that our GPU resources primarily consist of consumer-grade GPUs.

This project revolves around the exciting domain of generative AI within the context of fashion, offering an opportunity to contribute to cutting-edge research in this field.

Requirements/knowledge
The student is expected to have some background in deep learning, computer vision and some experience in training models. We use the Pytorch framework.

Terms
Credits: 30 ECTS (in agreement with the examiner)
Location: Linköping
Start: Jan. 2024

The selected candidate will receive a fixed payment of 30,000 SEK upon the successful completion of the project.

Contact
Farrukh Nauman, PhD, Applied AI and IoT, RISE Linköping (farrukh.nauman@ri.se)
Per Bröms, PhD, Applied AI and IoT, RISE Linköping (per.broms@ri.se)

Applications will be evaluated continuously, and the start date will be agreed with the successful applicant(s). We especially encourage underrepresented groups to apply and contribute their diverse perspectives to this valuable project.

Last application date is 22 of October, 2023.