{"id":33633,"date":"2023-06-02T14:52:29","date_gmt":"2023-06-02T13:52:29","guid":{"rendered":"https:\/\/www.innovationnewsnetwork.com\/?p=33633"},"modified":"2023-06-02T14:52:29","modified_gmt":"2023-06-02T13:52:29","slug":"how-can-the-efficiency-of-vision-transformer-ai-technology-be-improved","status":"publish","type":"post","link":"https:\/\/www.innovationnewsnetwork.com\/how-can-the-efficiency-of-vision-transformer-ai-technology-be-improved\/33633\/","title":{"rendered":"How can the efficiency of vision transformer AI technology be improved?"},"content":{"rendered":"
Researchers from North Carolina State University have developed a methodology that aims to improve vision transformers\u2019 ability to identify objects in images.<\/h2>\n
A vision transformer (ViT) is an AI technology that can identify and categorise objects in images.<\/p>\n
However, there are significant challenges related to decision-making transparency and computing requirements.<\/p>\n
Now, researchers have developed a new methodology that addresses both of these challenges.<\/p>\n
The method also improves the ability of a vision transformer to identify, classify, and segment objects in images.<\/p>\n
What are vision transformers?<\/h3>\n
Transformers are among the most powerful existing AI technology.<\/p>\n