no code implementations • 31 May 2022 • Jinyong Hou, Jeremiah D. Deng, Stephen Cranefield, Xuejie Din
To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential.
no code implementations • 22 Oct 2021 • Jinyong Hou, Xuejie Ding, Jeremiah D. Deng
In addition, to overcome the variations in medical images, the mean-teacher mechanism is utilized as an auxiliary regularization of the discriminator.
no code implementations • 21 Dec 2020 • Jinyong Hou, Jeremiah D. Deng, Stephen Cranefield, Xuejie Ding
Our key idea is to procure deep representations from one data domain and use it as perturbation to the reparameterization of the latent variable in another domain.
no code implementations • 25 Sep 2020 • Jinyong Hou, Xuejie Ding, Stephen Cranefield, Jeremiah D. Deng
Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains.
no code implementations • 17 Feb 2019 • Jinyong Hou, Xuejie Ding, Jeremiah D. Deng, Stephen Cranefield
Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains.