NeurIPS | Luis Herranz

Source-free unsupervised domain adaptation

Can we perform unsupervised domain adaptation without accessing source data? Recent works show that it is not only possible but also very effective. In

MeRGANs: generating images without forgetting

October 29, 2018March 8, 2021 continual learning, deep learning, generative adversarial networks, transfer learning

The problem of catastrophic forgetting (a network forget previous tasks when learning a new one) and how to address it has been studied mostly