A new study explores artificial intelligence in fashion

The use of artificial intelligence (AI) in the fashion industry has grown significantly in recent years. AI is used for tasks such as personalizing fashion recommendations for customers, optimizing supply chain management, automating processes and improving sustainability to reduce waste.

However, the creative processes in fashion design are still mostly driven by humans, and there is not much research in the field of using AI for fashion design. Moreover, studies are generally conducted with data scientists, who build AI platforms and are involved in the technology aspect of the process. However, the other side of this equation, i.e. the designers themselves, are not often involved in research.

In order to investigate the practical applicability of AI models for implementing creative designs and working with human designers, assistant professor prof. Yoon Kyung Lee from Pusan ​​National University in Korea conducted a detailed study. Her study was published in Thinking skills and creativity.

“At a time when artificial intelligence is so deeply embedded in our lives, this study instead began by considering what humans can do better than artificial intelligence,” says Prof. Lee, explaining his motivation behind the study. “Can there be effective collaboration between humans and artificial intelligence for creative design?”

Prof. Lee began generating new textile designs using deep convolution generative adversarial networks (DC-GAN) and cyclic GANs. The results of these models were compared with similar designs by design students.

The comparison revealed that although the designs produced by both were similar, the biggest difference was the uniqueness and originality seen in the human designs, which came from that person’s experiences. However, using artificial intelligence in repetitive tasks can improve designers’ efficiency and free up their time to focus on more difficult creative work.

AI-generated designs can also be used as a learning tool for people who have no expertise in fashion and want to explore their creativity. These people can create designs with the help of artificial intelligence. Therefore, prof. Lee proposes a human-artificial intelligence collaboration network that integrates GANs with human creativity to produce designs.

The professor also defined and studied the various elements of a complex system involved in the design of human-artificial intelligence collaboration. She also established a human-artificial intelligence model where a designer collaborates with an artificial intelligence to create a new design idea. The model is built in such a way that if the designer shares his creative process and ideas with others, the system can interconnect and evolve, improving his design.

The fashion industry can use this to predict changes in the fashion industry and offer recommendations and co-creation services. Setting goals, variables, and constraints is part of the designer’s job in a design environment for human-AI collaboration. Therefore, their work should go beyond just the visual aspect and instead cover different disciplines.

“In the future, everyone will be able to be a creator or designer with the help of AI models. Until now, only professional fashion designers could design and exhibit clothes. But in the future, everyone will be able to design the clothes they want and show their creativity,” concludes Prof. Lee.

Facilitated by Pusan ​​National University