High-Performance Approximate Domain Unlearning (IMAGE)

Tokyo University of Science

High-Performance Approximate Domain Unlearning

Caption

First proposal and realization of approximate domain unlearning—selective forgetting at the domain level for vision-language models.

Credit

Associate Professor Go Irie from Tokyo University of Science

Usage Restrictions

Cannot be reused without permission.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.