1 code implementation • 25 Mar 2022 • Mojtaba Bahrami, Mahsa Ghorbani, Nassir Navab
We show that training the agent against the prediction model can significantly improve the semantic features extracted for downstream classification tasks.
1 code implementation • 8 Apr 2021 • Mahsa Ghorbani, Mojtaba Bahrami, Anees Kazi, Mahdieh SoleymaniBaghshah, Hamid R. Rabiee, Nassir Navab
The soft pseudo-labels are then used to train a deep student network for disease prediction of unseen test data for which the graph modality is unavailable.