Artificial intelligence system Fashion ++ assists people with make fashion decisions

An research team at UT has built up a artificial intelligence system to improve individuals’ attire decisions.

Fashion++ is a program with the objective of making insignificant alters for outfit improvement, for example, changing the shading or attack of a bit of apparel, said Kimberly Hsiao, a computer science graduate student. She said she is driving the undertaking with UT computer science professor Kristen Grauman and students and professors from Cornell Tech, Georgia Tech and Facebook AI Research.

“We wanted to come up with something that is useful in peoples’ lives, and clothing is how people make statements about themselves,” Hsiao said.

Hsiao said the program works by clients transferring a photograph of their outfit. The AI makes a progression of recommendations to improve fashionability. She said the program was displayed at the International Conference on Computer Vision in Seoul, South Korea on Oct. 31.

The code for Fashion++ is posted on the project’s page for anybody to utilize. To show the AI what was in style, Hsiao said the research group fed Fashion++ 10,000 photographs from Chictopia, a design site where bloggers can post pictures.

Hsiao said the group anticipates persistently refreshing Fashion++ with new pictures and apparel for various body shapes.

“We do recommendations not only based on the user’s style preference, but also the user’s body by incorporating the user’s estimated model in the system,” Hsiao said.

Isay Katsman is a math and software engineering senior at Cornell Tech chipping away at the task. He said AI depends on monstrous informational indexes to perform well, yet Fashion++ is presently constrained by its littler informational collection.

“The bigger question for me is how we can productionize research to the point where people can incorporate the fruits of our effort into their everyday lives,” Katsman said.

Danny Lopez, correspondence studies and human relations junior, said Fashion++ can help individuals who are worn out on their style.

“There’s definitely a lot of people who care (about fashion) and I can see this being very helpful for people who are indecisive or have anxiety about what they should wear,” Lopez said.

Katsman said Fashion++ is only one way he sees artificial intelligence helping individuals manage their choices.

“I see the entire Fashion++ framework being a stepping stone more generally for useful generative models that help us answer unintuitive questions,” Katsman said.